← back to index
AI-Guidance.pdf
Text
Guidance, Considerations, & Intentions
for the Use of Artificial Intelligence
in West Virginia Schools
January 2024
| Version 1.0
wvde.us/ai-guidance
West Virginia Board of Education
2023-2024
L. Paul Hardesty, President
Nancy J. White, Vice President
F. Scott Rotruck, Financial Officer
Robert W. Dunlevy, Member
Victor L. Gabriel, Member
Daniel D. Snavely, M.D., Member
Christopher A. Stansbury, O.D., Member
Debra K. Sullivan, Member
Gregory F. Wooten, Member
Sarah Armstrong Tucker, Ph.D., Ex Officio
Chancellor
West Virginia Higher Education Policy Commission
West Virginia Council for Community and Technical College Education
Michele L. Blatt, Ex Officio
State Superintendent of Schools
West Virginia Department of Education
Version History
Given the rapidly changing landscape of artificial intelligence (Al) technology, it is expected that this
document will undergo regular updates to reflect the latest guidance and policy changes at both state
and national levels. For ease of tracking these updates, a summary table is included in the document.
This table succinctly lists the changes made in each new version to provide a clear and accessible
history of the document's evolution. This table allows readers to quickly reference how the guidance
has adapted over time, aligning with the latest legal, ethical, and technological developments in
Al. This approach better ensures that the document remains a relevant and reliable resource for
understanding current Al guidance and best practices in West Virginia schools.
Description of Changes Version
01/2024 Created initial document 1.0
Table of Contents
DRO CCH Oi scssssscccssscccsnsscnsanaccssnccenscancassnssanssasctsnsacsscuissnbuccuesusstéiwcscuscauabsseseisicbuiibascaattinciaaseuassusstaivesaccaasiwasaasscaacsusaseat 6
PUPP OSC sectsccasccieviisssscaana rie vesimn irises isananRREenRRTN TRI maT aT 6
Plat Of ACHON icviissssssccnceearnissinncace nrc i nnnnmenT at naRTeT RTT NRRRTTT ART oben TeRTECERTTAS 7
STC UCUULUIGS) (0 ent etter ec ererre 7
Al FOF EVOIrYOIG ssssscscsesnsnsesssssssssssssesesnssssssssosessesesnsssssssissssocsesessssiesssssssseesesesesssssssssnssoesesesnssssssssssssessecssssesesoessssssosesosssssosessess 9
AN Al EXxplainer.....s.cccsscscsssscsscecsscsssscecsseessseesssseesssnssssesssonesseuessenestsuesssesesussssuesseuesteueseeuesteuesseueseeueseanseucsssessseeseseesreneess 9
What is Generative Artificial Intelligence (AI)? vssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssss 9
How Does Generative Al WOPR?..cccsssssesssessssssssssssssssssssssssssssssssssesssssssnsssssssssssnsessessssssssssssssssssseassesssssasanssesssssssanesssssssssies 9
Why tal GDOUt Al NOW? uiccccsesssssssscssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssusssssssssssussssssssssssscsssusessussesssssssseecssseesessees 10
People in Charge ......sssscsscscsscsssscsssccsssecesscosssesesscocsscsessesesscsessesessecessecussesessesessesessesessesssesusscosscocsscoesseescoesesuesesueseoeess
Al Rights ANd RESPONSIDILITIES ...........csscecsssecsssecsssecsssecessecessecsssecsssecsssecessecessecsssecsssecessecsssecessecsesecsesecseseceeseceesacoets
Responsible USe Of Al TOOLS ...ccsssssssssssssssseessssssssessssssesssssssssessssseessssssussessssssessssssesssssssssesssssecssessssssssssssessssssenseesssssessssssesee
Al for EAUCATOIS..........ssecsssessssessssssssessssessssossssossssossssessssessssossssosassnsassosassosassosssosasosassosassossssossssosasssssossssosassosassossssosassoses
Guiding Principles for Al Use by Educators
Al if Gf EdtCational CONEKC ssissccsccieisisscescrncciesersneamcarn snr nennnna i ireimnca Tannen
COMMON ECUCATIONAL FFAMOWOFRS .recscscsssssssssssssssssssssscssssssssssssssssssssssssesssssssssssscsssssssnssssissssssninssssssssssisestsssssssnuaassesssssies
Al as ann Instrtictional, Enh an CO Me ttscviisssssscsscesccensssssicaaceernsenseaaainaneriarnnmnenmTancReTTN.
The INStFUCTIONGL OPPOFEUNILY .eeecsssesessssssesscsssssesssssssessesssssessssssessssssssssssssssssssssssssssssssusseesssssessssssessessssssesssssecseesssssessssssesee
Teaching Al.....ccsscscsscscsscessscsssccsssssesscsesscsessesessesesseoessesessecesseossucoussesesscossucsesucsesscsesucsesucoesecsesecsesussuesesseoesseoussesesscsesseoets
Teaching: StUG ENTS ADOUE Al sssvassssssecssasessesieeivernansnranaaniecesieenaniaevtannananinnainirnnntuaiinnintniian TAIN
COMPULALIONGL THINRING .ccsssccssssssessssssssesssssssessesssssessssssesssssssusessssssesssssssusessssssessssssesssssssssesssssecsssssssssesssssessssssenseessnssessesssesee
Equipping Future Ready Students
AdVaNnCiNg ACAGEMIC INTETITY........ssecsscecsssecsssecsssecsssecssersssecsssecsssersssecsesecsssecsesecsssecsssecsesecesseceesecoesecessecseseceesecoets
THE OPPOrtUNty..csscccsscsssessssssssesssssssssessssssessssssssesssssnesssssssssessssssesssssssnsesssssscssssssssssssssssssssssuesessssssessssssessessssssesssssecseesssssessssssesee 21
Recommendations for Advancing ACACeEMIC INtEGrity WIA Al .ecsssssssesssssssssssesssssssessssssssesssssseessesssssessssssese 21
A Variety of Different Al Platforims..........sssscsscsssscsssccsssccsssscsssccssscosssccssscossscsssecessecossecsssecossecessecessecsssersssecssseceeseets 22
Condensed Checklist for EAUCAtOIS.......s.ssssssssssecsscsssssssscscsessscssssssscsecescsecusssssscsscesenecusssssuceuceseuscusesssncesceseaseneesses 22
Al for Schools and County School Districts ............csssssssssscsossessssssessessssssssssssnssnssnsesnssnssnssasssnssnssnssassanssnssnssascansonsoness 23
EXISHING POLICIOS sssissssissssssssasssavsssassvsassvsavassavessasassassseawassavsssisavsasiseavassavsesisavsauisariisateiesi eavsiuidareisateion cease eRe 23
Guiding Principles for SChOOl ANd District Al USC.......scssscsssssssssssssecsssecsssecsssecsssecsssersssecsssecsssecsssecssseessseessseeees 23
Prohibited USe OF Al T0OlSissssisicsccesinssssnieae i ssnmacer inner enna Tanne TN TEATTEONS
StU ONL LOGIN. ceesssssssssssseessesssssessssssssssssssssessssssessssssssessssssscseesssnsessssssesssssssnsesssssecssssssusssssssnessssssussessssssessssssesssssssseesssaseeseesses
TEGCNEP SUPDOIMT scscesssccacscecusecexasececuseceeaaceeusaceeasareeusaceeaworevantaceeawcevancteaseetan ects veetun saat seevaa sacs weavan saa seav asa Coscavensaa oscars
School Management and Operations
Protecting Student Privacy and Safety .........scsssscsssscsssecsssecsssecsssecsssecsssecsssecsssecsssecssseesssecessecsssecesseeseseeseseeseseceets
SOCUTILY, PLIVACY, GNC SCPCLY .eccssssesssssssessssssssessssssssssssssssessssssessessssssssssssscssssssssesssssssssssssunsessssssessssssessessssssesssaseessesssnseessssses
EVQLUAtING Al PFOCUCES weccssssscesssssssssssssssesssssssssssssssscsssssssssssssssssssssssussssssssesssssssesessssssessssssessessssnsessssseessessssssesssssessssssensesssssees
Special CONSIAErAation: StUCENL AGC. ecccsssssssssssessesssssssssssseessesssssessssssesssssssnsesssssseses
Sample Considerations for Existing School and District Policies
Communicating with the COMMUNITY.........scsscscsssscsssscssecsssecsssecsssecsssecsssecsssecsssecsssecssseesssecssseessseessseessseesrseesseeeees
SUPPOTFtiNg Al iM INSTFUCTION .........cccecsssecsscecsscessssecsssecsssecsssecssseesssnesssnessenesseucssenesesucssenesteueseeesteeesteesteeseeneseeneseeets
MOVING FOR WAI ssscssssccsssscccssssscnsswstssnsseuscaucassicessecasctuinesssscissnbuscuesuesGBineseussiuiassbssssssasbuiabaccsauicsrbsssascassiaiwivecassoaaiaaiwetaae
ROPGPON COS iasisssssssssssssssssssnssssssssssssssssesnsssesetssssssssssesnessesetussecsssssutnessesstsssasssscsutnassesstssscsussssetnssstesasssitececesasssecesisasstececissssss
APP CHOICES sicssssccsscsscsnsscusscerscssssanssanccessasssanssauenessnesnsstesnsscusctettsstasanssantesstecusensinssnussusssstesenscusccusstucsinincsscadssensesncaantesiees
Appendix 1 — Canvas Self-Enrolling RESOUrCE DIreCtOTy ......s.scsssscsssscsssecssecsssecessecessecessecessecessecessersssecesseceets
APPONAiX 2 — GLOSSALY.......ssecsssscsscessecessccessecesscsesscsesscocsscocsscsesscsesscoesscoesscsesscousscsssecsesecsesecsssecassecsesecassecsesucseceeeseoets
APPeNdixX 3 — CHECKLISt........cccsscscsscecsccessccessccessccessecesscoesscsesscoesscsesscossucossscsesscoesecoesecsesecsesecossecossecsesecsssecsesucsecoessceets
Introduction
Purpose
This guidance centers around the users of artificial intelligence (Al) in various roles throughout
West Virginia PK-12 schools. It is designed to assist individuals such as superintendents, district
staff, educators, and support staff in the appropriate and effective use of Al, particularly generative
Al technologies, within West Virginia schools. Its focus includes classroom instruction, school
administration, and the broader scope of district operations. While recognizing the significant
opportunities Al presents for enhancing educational experiences in West Virginia, this document
also addresses the need for careful oversight to minimize risk and ensure responsible use. Note that
multiple existing West Virginia Board of Education (WVBE) policies include language that are relevant
to the use of technologies such as Al. This guidance supports those policies and in no way supersedes
those policies.
Knowing the need for multiple levels of support related to Al in West Virginia schools, the
West Virginia Department of Education (WVDE) developed a Canvas resource site accessible
through the self-enrolling resource directory at hitp://wvde.instructure.com. This site will serve as a
comprehensive hub, offering a variety of materials and resources for both county school districts and
educators. Concurrently launching with this guidance, the site will be continuously updated with new
resources as they are identified and curated. For instructions on how to access this resource site in
Canvas, see Appendix 1.
Note: The WVDE is a Participating Government Agency in the work of TeachAl. This guidance was
informed by the work of TeachAl (TeachAl.org) which operates under a Creative Commons license
(CC BY-NC-SA 4.0). This work was adapted and modified under the license to meet the needs of West
Virginia educators, schools, and districts, and as such, this work is published under the same license,
allowing the work to be shared and adapted for non-commercial purposes.
Plan of Action
The release of this guidance initiates the support the WVDE is providing to schools and districts with
the use of Al in education. An overarching plan of action below highlights the WVDE’s commitment to
provide support with using Al, part of which is addressed within this guidance.
Ifthe WVDE supports school and district use of artificial intelligence by:
- Reinforcing that people are ultimately in
control over Al and cannot be replaced by it
- Advancing educators’ familiarity and comfort
with Al
- Encouraging the use of Al to enrich and
streamline instructional methods
* Upholding academic integrity in Al
applications
- Safeguarding student wellbeing and data
privacy in Al usage
Then the responsible application of Al can lead to:
- Individualized learning experiences that
cater to each student's needs
- Improved accessibility for students with
diverse learning needs and exceptionalities
- Streamlined administrative tasks, freeing up
- Clarifying ethical uses of Al in education
- Aligning Al with existing educational
frameworks
* Equipping educators with the knowledge for
teaching students about Al
- Facilitating open and transparent dialogue
about Al with all involved parties
- Instantaneous feedback and evaluation
for students
- Acquisition of necessary skills for the
workforce of today and tomorrow, such as
knowledge of computer science and data
more time for educators to teach literacy
Statement of Need
Artificial intelligence is rapidly changing the landscape of education. West Virginia public schools,
along with all schools throughout the nation, face the monumental task of learning these emerging
technologies and being able to use them in safe and responsible ways. The risks of Al are sometimes
overstated (e.g., the extinction of people). These overstatements often come from unfamiliarity with or
surface-level misunderstandings of Al. Other times, they arise from competing financial interests that
desire to limit open-source competition. However, it is fundamental that realistic risks are assessed
and addressed in order to protect students and staff. Predictable risks include over-reliance on Al
technologies, challenges to independent and creative thinking, reduced social interactions, privacy
and safety issues, furthering of digital divides, as well as plagiarism and cheating. It is imperative that
West Virginia schools and districts demonstrate proactive preparedness to answer these challenges.
It would be unfortunate to view the educational opportunities of Al as an issue that cannot be managed.
As with the integration of all other technologies into our daily lives, Al will not be an exception. As Al
technologies progress, they will become an increasingly seamless part of how we use technology and
will eventually be indistinguishable in many respects, much in the same way that we interact with
smartphones that already use Al (e.g, auto-complete, text-to-speech functionality). Likewise, students
should be informed of the possible ways in which Al will impact the job market they will eventually enter.
[7 |
We must distinguish between innovation with Al compared to Al with innovation. This distinction is
where our educators, and those who support them, make the difference. As Al continues to emerge
and provide innovations (Al with innovation), educators will ultimately continue to innovate using Al
(innovation with Al).
AI for Everyone
An Al Explainer
What is Generative Artificial Intelligence (Al)?
It is important to define Al to ensure that those who access this
guidance document are speaking the same language. Al is computer
code that can resemble human intelligence to complete a given task
(e.g. problem-solving, planning, etc.). It involves developing algorithms
and systems that can perceive, reason, learn, and make decisions
based on data.
Artificial intelligence includes a wide array of technologies, each
applied in different fields and industries. These include drones used
in delivery, advanced medical diagnostics systems, Al-driven predictive
maintenance in manufacturing, smart home devices, personalized
learning platforms for language acquisition, and sophisticated
algorithms for financial market analysis. Though Al has applications
across many fields, such as those mentioned above, this guidance is
focused on Al applications that generate new content. Examples of
“generative Al” applications include Bard, Copilot, ChatGPT,
Mid-Journey, and Dall-E’ These technologies are built on large
language models (LLMs) that can produce new content, such as text,
images, or music, based on patterns they have learned from their
training data and use natural language processing (NLP) to provide
human-like responses. It is important to acknowledge that while this
Natural Language
Processing (NLP) - a field
of artificial intelligence
that focuses on enabling
computers to understand,
interpret, and respond
to human language Ina
meaningful way.
Large Language Model
(LLM) - a sophisticated
Al system trained on
extensive text data to
process and produce
language; recognize
patterns, grammar, and
nuances. It can perform
tasks like text generation,
question answering, and
language translation.
guidance is specific to technologies current at the date of publication, Al is advancing quickly, and
new platforms and resources will continue to emerge?
How Does Generative Al Work?
It is important to note how generative Al works. Generative Al works by analyzing large datasets to
learn patterns and features, which it then uses to generate new, original content. It uses complex
algorithms, often based on neural networks, to make predictions based on the input data it has
processed; thereby enabling it to create a wide range of outputs, from text and images to music and
code, that mimic the style or characteristics of the data on which it was trained.
'Code.org, CoSN, Digital Promise, European EdTech Alliance, Larimore, j., and PACE (2023). Al Guidance for Schools Toolkit. Retrieved
from http://teachai.org/toolkit. [November 30, 2023].
? OpenAl. (2023). ChatGPT (September 25 Version) [Large language model]. https://chat.openai.com.
3 Oregon Department of Education. (2023). Generative Artificial Intelligence (Al) in K-12 Classrooms. Retrieved from https://www.oregon.
gov/ode/educator-resources/teachingcontent/Documents/ODE Generative Artificial Intelligence (Al) in K-12 Classrooms 2023.pdf
[November 16, 2023].
Lo |
At its core, generative Al “predicts the flows of language. Trained on .
massive amounts of text taken from publicly available internet sources Algorithm - A set of rules
to recognize the relationships that most commonly exist between or instructions guiding Al
individual units of meaning (including full or partial words, phrases, operations and decision-
and sentences), LLMs can, with great frequency, generate replies to making.
users’ prompts that are contextually appropriate, linguistically facile,
and factually correct.” Neural Network - A type of
artificial intelligence that
While this technology does mimic human interactions, generation mimics the workings of the
of ideas, and decision-making, it is important to note that as an Al human brain to process
“generates a reply, it is not making factual assessments or ethical information and make
distinctions about the text it is producing; it is simply making decisions.
algorithmic guesses at what to compose in response to the sequence
of words in your prompt.”
“Either way, it’s all just math and programming.”
- Reid Hoffman
Why talk about Al now?
The increasing use of Al in education, notably with the advent of generative Al technologies like
ChatGPT, Bard, and Copilot has brought significant changes in how educators, students, and families
interact with technology. These advancements, while offering transformative potential, also necessitate
careful decision-making by schools and districts. Clear, student privacy-centered policies are essential
to ensure developmentally appropriate access for all students.
As with any new technology, from the internet to smartphones, generative Al presents both opportunities
and challenges in educational settings. To navigate these effectively, several organizations are providing
guidance and resources for the responsible use of Al in education and for teaching about Al itself. These
efforts aim to support effective and inclusive educational practices in the era of Al.
Selected examples of these resources and organizations include:
- Teach Al, a partnership between major education organizations, including Code.Org,
International Society for Technology in Education (ISTE), the World Economic Forum, National
Association of State Boards of Education, National School Boards Association, Educational
Testing Service, and Khan Academy, was developed in an effort to provide guidance to
policy-makers and educational leaders around Al in education.
- The CRAFT (Classroom-Ready Resources About Al For Teaching Project), developed by Stanford
University’s Graduate School of Education and provides resources to support high school
teachers in increasing students’ Al literacy.
“Hoffman, R. (2023). impromptu: Amplifying our Humanity Through Al. Dallepedia.
5 Hoffman, R. (2023). !mpromptu: Amplifying our Humanity Through Al. Dallepedia
[|
- The Hands-On Al Projects for the Classroom from ISTE and General Motors (GM) has developed
guides for elementary and secondary teachers to support student-driven learning related to Al
and its impacts on society.®
People in Charge
lt cannot be overstated that the fundamental principle of using Al to bolster educational efforts must
be a balanced and people-centered endeavor. This intention is generally described as having “humans
in the loop.” Without acknowledging and reinforcing that people are in charge and responsible for
the safe application of Al, the whole vast machinery of Al would be void of educational purpose
and benefit. Al technologies alone have not guided their own development nor prescribed their
characteristic form. Spurred as a means of task automation and problem-solving, Al requires cautious
use with people steering it. Therefore, it is helpful to think of Al in familiar terms. The figure below
captures six analogies that describe Al in more concrete terms while recognizing the limitations of
Al and the need for responsible human control and input. While the figure does not fully capture
the extensive complexities, challenges, and far-reaching implications of Al applications, highlighting
certain features in familiar terms is a Suitable first step.
Artificial Intelligence is like a...
Personal Coach
It can highlight areas of
improvement, but it is
up to us to take action.
as
Library
It holds a wealth of
knowledge and resources,
but it is up to us to
think critically.
Va
Toolbox
It provides us with a
variety of tools to adapt
to different needs and
experiences, but it is up to
us to use them responsibly.
”
Canvas
It provides a space for
individual expression and
exploration, but it is up to us
to create the masterpiece.
<=
am
Spotlight
It can illuminate new ways
of learning, but it is up
to us to make sure that it
doesn’t cast a shadow on
creativity.
Bridge
It can connect us to new
topics and ideas, but we
must be in the driver seat.
6 Oregon Department of Education (2023). Generative Artificial Intelligence (Al) in K-12 Classrooms. Retrieved from https://www.oregon.
ov/ode/educator-resources/teachingcontent/Documents/ODE Generative Artificial Intelligence (Al) in K-12 Classrooms 2023.pdf
[November 16, 2023]
[om |
Al Rights and Responsibilities
Responsible Use of Al Tools
The appropriate application of Al in educational settings depends greatly on the specific context,
such as classroom projects or tasks. Utilizing Al tools responsibly demands extra dedication
and understanding. For instance, educators must clearly define the conditions and methods for
incorporating Al into their teaching strategies. Simultaneously, school districts are tasked with
adhering to relevant legal standards concerning data protection and student data privacy. The
educational goals of each educational activity will determine the suitable Al technology to be used for
that particular task.’
Potential examples of the responsible use of Al to meet educational goals in West Virginia classrooms
can be found below.
District Management and Operations
» Communications: Al tools could potentially help draft and refine communications within the
school community, utilize chatbots for routine online inquiries, or provide instant language
translation when a translator is unavailable.
» Operational Efficiency: Staff could use Al tools to support school operations and streamline
administrative processes, including scheduling courses and calendars, automating inventory
management, or increasing energy savings.
» Learning Management Systems (LMSs): Al that is natively incorporated into learning
management systems by the system vendor has the potential to help analyze student
performance data to provide insights to educators, helping them tailor instruction or
interventions. These types of Al will fall under the memorandum of understanding (MOU)
between the district and the system vendor, thus allowing the analysis of data by the Al, but
also protecting student data. These types of analyses, along with classroom and school-based
observations, can give insight into meeting the needs of the whole child.
Educator Support
» Assessment Design and Analysis: In addition to enhancing assessment design by creating
questions, Al analysis algorithms within district-approved learning management systems could
provide standardized feedback on common mistakes. Al could conduct diagnostic assessments
to identify gaps in knowledge or skills and enable rich performance assessments. Educators
would be responsible for data analysis and evaluation, feedback, and grading, including
determining and assessing the usefulness of Al in supporting their work.
» Resource Development and Support for Differentiation: Al could assist educators by
differentiating resources, suggesting lesson plan components, generating diagrams and charts,
and customizing opportunities for independent practice based on educator-developed criteria
and various student proficiency levels.
7 Adapted from Gallagher, H. A, & Cottingham, B. W. (2023, June). The urgent need to update district policies on student use of artificial
intelligence in education [Commentary]. Policy Analysis for California Education. https://edpolicvinca.org/newsroom/urgent-need-
update-district-policies-student-use-artificial-intelligence-education.
Le |
»
Provide Continuous Professional Learning: Al could guide educators by recommending teaching
and learning strategies based on educator-developed scenarios, suggesting professional
learning resources that are related to teachers’ interests, suggesting collaborative projects
between content areas or teachers, and offering simulation-based training scenarios such as
teaching a lesson or managing a parent-teacher conference.
Research and Resource Compilation: Al could help educators by recommending books, articles,
research, and teaching strategies relevant to a lesson.
Student Learning
»
Aiding Creativity: Students could use generative Al to spark creativity across diverse subjects,
including writing, visual arts, and music composition.
Collaboration: During collaborative group projects, students could collectively leverage
generative Al tools as a means to brainstorm ideas, support their research efforts, and identify
relationships among various findings.
Communication: Al can offer students real-time translation, personalized language exercises,
and interactive dialogue simulations.
Content Creation and Enhancement: Al can help generate personalized study materials,
summaries, quizzes, and visual aids, and help students review content.
Tutoring: Al technologies have the potential to make available one-to-one tutoring and support
for every student with access to the technology, making personalized learning more accessible
to a broader range of students. Al-powered virtual teaching assistants could provide non-stop
support, answer questions, help with homework, and supplement classroom instruction.
Critical Analysis and Discernment: While Al usage by our youngest learners is not appropriate, it
is important to teach them to critically analyze and discern Al-generated materials accessed and
presented by their teacher. This approach fosters early development in critical thinking, enabling
young students to distinguish between potentially inaccurate Al-created content and human-
generated information, but also allows young students to learn how Al works.
AI for Educators
Guiding Principles for Al Use by Educators
The following guiding principles are put forth to guide educators in the safe use of Al and address
current and future educational goals, teacher and student agency, academic integrity, and security. It is
recommended that educators commit to adopting procedures to implement each principle.
»
| may use Al to help all my students achieve their educational goals. If | choose to use Al,
in a manner consistent with my district policies, | will use Al to help my students reach their
educational goals, including improving student learning and my own effectiveness. | am
committed to evaluating Al tools for biases and ethical concerns, ensuring they effectively serve
my students.
| reaffirm adherence to existing policies and regulations. Al is one of many technologies used
in classroom instruction, and | will use it in alignment with existing policies and regulations
to protect student privacy, ensure accessibility to those with disabilities, and protect against
harmful content. | will not share personally identifiable information with consumer-based Al
systems. | understand that there is a difference between Al that is integrated into technologies
purchased by my district, such as our LMS or an assessment platform, and a consumer-based
Al system that | purchase or access on my own. | will thoroughly evaluate existing and future
technologies and address any gaps in compliance that might arise.
| will educate myself about Al. Promoting Al literacy among students is central to addressing the
risks of Al use and teaches critical skills for students’ futures. | will do my best to learn how to
use Al, when to use It, and how it works, including foundational concepts of computer science
and other disciplines.
| will explore the opportunities of Al and address the risks. In a way that is appropriate for my
classroom, | will work to realize the benefits of Al in education, address risks associated with
using Al, and evaluate if and when to use Al tools, paying special attention to misinformation
and bias.
| will use Al in my classroom to advance a culture of academic integrity. Honesty, trust, fairness,
respect, and responsibility continue to be expectations for both my students and myself. | will
expect students to give credit to sources and tools and be honest in presenting work that is
genuinely their own for evaluation and feedback.®
Al in an Educational Context
Common Educational Frameworks
The process of instructional planning begins with identifying the specific standards that the lesson
aims to address. These standards outline the key knowledge and skills students are expected to
master. Educators then design instructional objectives that align with these standards, ensuring that
8 Code.org, CoSN, Digital Promise, European EdTech Alliance, Larimore, J, and PACE (2023). Al Guidance for Schools Toolkit. Retrieved
from http://teachai.org/toolkit. [November 30, 2023].
[ «|
the learning activities and assessments are directly tied to the desired outcomes. Al can be used asa
supporting tool, rather than a replacement, for this process. Al, like many other technologies, can be
used in multiple applications in classrooms. Many West Virginia educators may have received training
in different models of technology integration. Examples of the use of Al in classrooms through the lens
of an example technology integration framework is included below.
The SAMR model, developed by Dr. Ruben Puentedura, categorizes technology integration into four
levels: Substitution, Augmentation, Modification, and Redefinition.? The table below illustrates how
generative Al applications in the classroom can fit into each level of the SAMR model, as described
with examples that may be suited for secondary classrooms:
SAMR Level Description Generative Al Student-Centered Example
Substitution Technology acts as a direct Students use an Al tool to look up detailed
substitute for traditional information for a research project, similar to
methods, with no functional searching in a textbook.
change.
Augmentation Technology acts as a Students use Al for language translation
substitute, but with functional in a foreign language class, whereby the
improvements. tool provides functional improvement by
understanding idioms, proverbs, and other
common expressions that may not have ideal
literal translations.
Modification Technology allows for Students complete personalized learning
significant task redesign. projects using Al to create new products and
receive immediate and personalized feedback
that is tailored to their level of progress.
Redefinition Technology allows for the Students engage in an immersive virtual
creation of new tasks, reality simulation experience wearing a
previously inconceivable. headset. An Al-powered program could be
used to initially guide students through the
process of changing the motor oil in a vehicle
in a safe and controlled environment, where
both the instructor and Al could provide
real-time feedback and instructions, with the
possibility of projecting the simulation on
a screen for other students to observe and
learn as well.
9 Puentedura, R. (2006). Transformation, technology, and education [Blog post]. Retrieved from http://hippasus.com/resources/tte/
[ » |
Al as an Instructional Enhancement
The Instructional Opportunity
As generative Al continues to advance, it will become increasingly important to design student
learning tasks that require critical thinking, creativity, and personal insights—skills that Al cannot
replicate. This approach ensures students demonstrate that they are actively engaged in their learning
processes, developing abilities that are uniquely human and that cannot be outsourced to Al, thereby
fostering deeper understanding and intellectual growth.
For example, Suppose students are assigned a list of vocabulary words, asked to write the definition of
each word, and tasked with using the word in a sentence. A student could quickly write the following
prompt in an Al platform such as ChatGPT:
Prompt: For each word in this list, please write a definition of the word and then write the word in
a sentence. Write in the manner of an 8th grader. Word list - abate, assimilate, concede, dissipate,
erratic, flourish, impulsive, longevity, malleable, obstruct, render, rueful, subordinate, tarry,
transgression.
In less than 30 seconds, ChatGPT could return text like that shown below for every vocabulary word,
which could be copy/pasted and submitted to a teacher:
ChatGPT output:
* Abate - (verb) To become less intense or widespread.
» Sentence: After the storm, the wind started to abate, and the rain became lighter.
* Assimilate - (verb) To understand and become a part of a new culture or group.
» Sentence: When Maria moved to a different country, it took some time for her to
assimilate into her new school and make friends.
* Concede - (verb) To admit that something is true or to give up in an argument.
» Sentence: Even though he didn’t want to, Mark had to concede that his friend’s idea
was better for their project.
To counter this situation and best support student learning and engagement, the educator could
instead request that ChatGPT develop an alternative to the previously designed vocabulary
assignment. This places emphasis on the understanding that the educator's expertise and teacher-
student connections are crucial to successfully implementing Al as an instructional tool.
In the example below, the educator could use ChatGPT to develop ideas for an alternative assignment:
Prompt: You are an eighth-grade teacher. Develop 6 different 10-minute classroom activities to aid
students in understanding the meaning of this list of words: abate, assimilate, concede, dissipate,
erratic, flourish, impulsive, longevity, malleable, obstruct, render, rueful, subordinate, tarry,
transgression.
OpenAl. (2023). ChatGPT (September 25 Version) [Large language model]. https://chat.openai.com,
[|
ChatGPT Output:
Certainly! Here are six 10-minute classroom activities to help students understand the meaning of the
words in your list:
¢ Word Match-Up (5 minutes):
» Prepare flashcards with the words on one side and their definitions on the other.
» In pairs or small groups, students must match each word with its correct definition
within a time limit of 5 minutes.
» The group that matches all the words correctly first wins.
* Word Charades (10 minutes):
» Write each word on separate pieces of paper and put them in a hat or container.
» One student draws a word and acts out its meaning without speaking while the class
guesses what word it is.
» Seta timer for 2 minutes per word. After each round, discuss the word's meaning as a
class.
* Sentence Scramble (10 minutes):
» Write a sentence for each word on the board, but scramble the words within each
sentence.
» Challenge students to unscramble the sentences and identify the correct word for each
definition.
» Discuss the meaning of each word in context once the sentences are unscrambled.
* Vocabulary Story (10 minutes):
» Give students a list of 3-4 words from your list.
» Ask them to create a short story or paragraph using all the words correctly.
» Encourage them to be creative and share their stories with the class, discussing the
meanings of the words as they read.
* Word Web (10 minutes):
» Choose one word from the list and write it in the center of the board.
» Ask students to brainstorm related words, synonyms, and antonyms connected to that
word,
» Discuss how these related words help us understand the word’s meaning.
¢ Word Illustrations (10 minutes):
» Assign each student a word from the list and provide them with paper and art
supplies.
» Instruct students to create an illustration or visual representation of their word's meaning.
» Have students present their illustrations to the class and explain how their artwork
represents the word.
These activities should engage students in various ways and help reinforce their understanding of the
meanings of the words on your list. ”
The educator could then adapt these activities based on their knowledge of the students in his or
her classroom to best meet the instructional needs of these students. The educator could also use
prompts like those following to develop additional lesson ideas for the same set of vocabulary words,
allowing for assignments that engage students, and don’t allow for Al to complete the assignments.
" OpenAl. (2023). ChatGPT (September 25 Version) [Large language model]. https://chat.openai.com,
[7 |
Prompt: For the same word list, create a list of words and definitions that | can use to create a
reference resource for students.
Prompt: Using the same list of words, generate 6 different paragraphs about growth mindset with each
paragraph containing at least 7 of the words in each paragraph for the purpose of student annotation
with the purpose of generating three questions for discussion. Please use all 15 words in the list
among the 6 paragraphs. Bold each of the words in the word list in the paragraphs.
In the age of Al, educators are encouraged to update their assignments to increase the complexity to
such a degree that the requirement for personal student input and engagement is required.
Within the WVDE Canvas Course, WVDE Professional Learning Resource for Artificial Intelligence,
educators will find the complete output of the prompts above. Instructions on accessing Canvas
resources can be found in Appendix 1.
Teaching Al
Teaching Students About Al
Al is a branch of computer science that focuses on creating computer programs capable of performing
tasks that typically require human intelligence. It involves developing algorithms and systems that can
perceive, reason, learn, and make decisions based on data. WVBE Policy 2520.14 (West Virginia College-
and Career-Readiness Standards for Technology and Computer Science) requires that all students
receive grade-appropriate computer science instruction throughout the K-12 experience. As a branch
of computer science, Al provides a unique and engaging opportunity to demonstrate the power of
computer science through technologies that impact student lives directly.
Knowing how AI processes data and generates outputs enables students to think critically
about the results AI systems provide. They can question and evaluate the information they
receive and make informed decisions. This is of particular significance as students utilize
Al in the classroom, to maintain academic integrity and promote ethical use of AI.”
In addition to computer science instruction, students should be taught Al literacy. Al literacy refers
to the knowledge, skills, and attitudes associated with how artificial intelligence works, including
its principles, concepts, and applications, as well as how to use artificial intelligence, such as Its
limitations, implications, and ethical considerations.” At its most basic, Al literacy can be taught
through a lens of computational thinking — a foundational principle in computer science.
® CDOE (2023). Learning With Al, Learning About Al, Retrieved from https://www.cde.ca.gov/pd/ca/cs/aiincalifornia.asp#:~:text=CDE%20
encourages%20educators%20to %20approach,promote%20ethical%20use%200f%20technology. [November 30, 2023].
® Code.org, COSN, Digital Promise, European EdTech Alliance, Larimore, J., and PACE (2023). Al Guidance for Schools Toolkit.
Retrieved from http://teachai.org/toolkit. [November 30, 2023].
Le |
Cybersecurity
Robotics
Data
Science
Computer
Science
* Algorithmic Thinking: Understanding Al involves learning about the algorithms that drive
decision-making processes, from basic algorithms like sorting data to more advanced
ones used in predictive modeling. Students enhance their algorithmic thinking skills by
understanding how these step-by-step instructions guide Al behavior.
* Debugging: Al systems, like those used in autonomous vehicles, must be meticulously
debugged to ensure accuracy and safety. Students engaged in Al learn about debugging by
identifying and correcting errors in Al algorithms, gaining insight into how even small errors
can significantly impact an Al system's performance.
* Evaluation: In Al applications such as restaurant and product recommendation systems,
different algorithms are evaluated to determine which provides the most relevant results.
Students learn about the evaluation aspect of computational thinking by comparing Al models,
assessing their effectiveness, and refining them for improved outcomes.”
Equipping Future Ready Students
WVBE Policy 2520.14 (West Virginia College- and Career-Readiness Standards for Technology and
Computer Science) is designed to provide opportunities for students to learn computer science and
technology principles to such a degree that upon mastery of these topics they become an empowered
learner, a digital citizen, a knowledge constructor, an innovative designer, a computational thinker, a
creative communicator, and a global collaborator.
Learning about Al transforms students into versatile learners and global citizens. They gain mastery
over their education using Al’s personalized tools, develop a keen understanding of digital ethics, and
construct new knowledge by critically analyzing information produced by Al. Al encourages innovation
as students creatively solve complex problems and enhance their problem-solving skills. Additionally,
Al aids students in creative communication, enabling them to produce unique digital content. It also
promotes global collaboration, potentially connecting them with peers worldwide and expanding
their perspectives. Overall, Al has the potential to equip students with essential 21st century skills,
preparing them for a positive societal impact and effective navigation of the digital landscape.
Policy 252014 specifies that our youngest learners are to learn about algorithms, data, staying safe
online, and how computing is changing over time.” Similarly, our high school students are expected
to understand algorithms, how computing works, and how to use coding and computers to advance
society.
“ Code.org, CoSN, Digital Promise, European EdTech Alliance, Larimore, J, and PACE (2023). Al Guidance for Schools Toolkit. Retrieved
from http://teachai.org/toolkit. [November 30, 2023].
5 WVBE Policy 2520.14, West Virginia College- and Career-Readiness Standards for Technology and Computer Science, https://apps.sos.
wv.gov/adlaw/csr/readfile.aspx?Docid=50990&Format=PDF#page=15
© WVBE Policy 2520.14, West Virginia College- and Career-Readiness Standards for Technology and Computer Science, https://apps.sos.
wv.gov/adlaw/csr/readfile.aspx?Docid=50990&Format=PDF#page=18
| > |
Advancing Academic Integrity
The Opportunity
The arrival of Al in education presents a unique opportunity to revisit and even advance the principles
of academic integrity. This technological development should encourage educators and institutions
to redefine and reinforce the values of honesty, trust, fairness, and responsibility in academic work.
Al tools have the potential to be used to educate students about the nuances of ethical research and
writing, helping them understand the importance of originality and the consequences of plagiarism.
However, the key lies in using Al as an educational tool that fosters a deeper appreciation for the
integrity of learning. By integrating Al into classroom instruction, educators can create a learning
environment that emphasizes critical thinking, creativity, and ethical reasoning, preparing students to
navigate complex academic and professional landscapes with integrity.
In light of Al in education, it is necessary to address plagiarism and other risks to academic integrity.
This requires revisiting policies about academic integrity and providing opportunities for educators
and students to commit to using Al to advance the fundamental values of academic integrity —
honesty, trust, fairness, respect, and responsibility.” WVBE Policy 4373, Appendix A, addresses both
cheating and technology misuse. Both of these behaviors could be considered if Al were to be used
inappropriately. Consequences could be: academic sanctions, revocation of privileges, administrator/
student conference, parent contact, parent-teacher conference, detention, denial of participation in
class and/or school activities.
Recommendations for Advancing Academic Integrity with Al
Educators may decide to permit the use of generative Al tools for certain parts or types of
assignments, providing clear explanations for its restricted use and outlining the reasons for
prohibiting it in other tasks.
As of the release of this guide, it is advised that educators refrain from using programs that
claim to detect the use of generative Al for cheating or plagiarism purposes due to concerns
about their reliability.
Whenever a teacher or student uses an Al system, it is imperative to openly acknowledge and
describe its usage. Furthermore, students are required to reference any Al tools they utilized in
their work as part of this transparency. See the following resources for support:
» MLA Style - Generative Al
» APA Style - ChatGPT
» Chicago Style - Generative Al
7 International Center for Academic Integrity [ICAI]. (2021). The Fundamental Values of Academic Integrity. (3rd ed).
https://academicintegrity.org/about/values.
%® WVBE Policy 4373, Expected Behavior in Safe and Supportive Schools, https://apps.sos.wv.gov/adlaw/csr/readfile.
aspx?Docld=51038&Format=PDF#page=25
A Variety of Different Al Platforms
There are new Al platforms launching each day. It is important to note that many of these platforms are an
interface between the user and another Al system, such as ChatGPT-4. It is necessary to review the terms
and conditions for each system and review county school district policies before using that system.
A brief sampling of different Al tools stakeholders have reported using Is included below:
ChatGPT ChatGPT, developed by OpenAl, is a generative Al platform designed to interpret
and respond to prompts with detailed answers.
Copilot Copilot is a conversational Al service developed by Microsoft, offering users the
ability to interact in the Edge browser in a natural, dialogue-based format for
information retrieval and various online tasks.
Bard Bard, created by Google, is a generative Al platform that responds to prompts
with detailed answers, having been trained to understand and follow specific
instructions.
DALL-E DALLE, an Al system from OpenAl, generates realistic images and artwork based
on descriptions provided in natural language.
MagicSchool.ai MagicSchooLai is an innovative suite of Al-powered tools designed to assist
teachers in various aspects of classroom management and instruction.
NotionAl NotionAl employs artificial intelligence to assist with organization and project
management.
Question Well Question Well creates key questions, learning objectives, and corresponding
multiple-choice questions, offering export options to various educational
technology platforms.
The West Virginia Department of Education does not endorse or recommend any particular program
but provides resources for informational purposes.
Condensed Checklist for Educators
While creating an exhaustive checklist would be an ambitious endeavor, the WVDE has compiled
a concise one-page checklist (see Appendix 3) for classroom educators. This checklist includes
key points that could assist educators as they contemplate incorporating Al technologies in their
classrooms. It is important to note that using the checklist is not mandatory but is offered as a helpful
starting place when considering responsible Al use throughout instructional design and delivery.
[ 2 |
AI for Schools and County School Districts
Existing Policies
The WVDE has identified policies that may impact Al usage. This list is not exhaustive and may
grow over time. It is recommended that districts review these policies and use these policies when
evaluating Al technologies. All WVBE policies can be reviewed at https://wvde.state.wv.us/policies/.
2460 —- Educational Purpose and Acceptable Use of Electronic Resources, Technologies and the
Internet
4350 — Procedures for the Collection, Maintenance and Disclosure of Student Information
- 2419 — Regulations for the Education of Students with Exceptionalities
* 2520.14 - West Virginia College- and Career-Readiness Standards for Technology and Computer
Science
4373 — Expected Behavior in Safe and Supportive Schools
Guiding Principles for School and District Al Use
The following guiding principles and commitments are put forth to guide the appropriate and safe
use of Al and address current and future educational goals, teacher and student agency, academic
integrity, and security. It is recommended that districts, staff, schools, administrators, and educators
commit to adopting procedures to implement each principle. For the commitments below, the “we”
refers to the school or county school district.
- We can use Al to help all of our students achieve their educational goals. If we choose to
use Al, we will use Al to help us reach our school goals, including improving student learning,
teacher effectiveness, and improving school operations. We will aim to make Al resources
universally accessible, focusing especially on bridging the digital divide among students and
staff. We are committed to evaluating Al tools for biases and ethical concerns, ensuring they
effectively serve our educational community.
* We reaffirm adherence to existing policies and regulations. Al is one of many technologies
that may be used in West Virginia schools, and its use will align with existing policies and
regulations to protect student privacy, ensure accessibility to those with disabilities, and
protect against harmful content. We will not share personally identifiable information with
consumer-based Al systems. We will thoroughly evaluate existing and future technologies and
address any gaps in compliance that might arise.
* We will proactively educate our staff and students about Al. Promoting Al literacy among
students and staff is central to addressing the risks of Al use and teaches critical skills for
students’ futures. Students and staff will be given support to develop their Al literacy, which
includes how to use Al, when to use It, and how it works, including foundational concepts of
computer science and other disciplines. We will support teachers in adapting instruction in a
context where some or all students have access to generative Al tools.
* We will explore the opportunities of Al and address the risks. In continuing to guide our schools,
we will work to realize the benefits of Al in education, address risks associated with using Al, and
evaluate if and when to use Al tools, paying special attention to misinformation and bias.
- We will use Al to advance a culture of academic integrity. Honesty, trust, fairness, respect, and
responsibility continue to be expectations for both students and teachers. Students should
[ = |
be truthful in giving credit to sources and tools, and be honest in presenting work that is
genuinely their own for evaluation and feedback.
* We will maintain student and teacher agency when using Al tools. Al tools can provide
recommendations or enhance decision-making, but staff and students will serve as “critical
consumers” of Al and lead any organizational and academic decisions and changes. When Al is
employed for decision-making, we understand that humans, and not the Al, will be responsible
and accountable for pedagogical or decision-making processes.
* We will commit to auditing, monitoring, and evaluating our school’s use of Al. Understanding
that Al technologies are evolving rapidly, we commit to frequent and regular reviews and
updates of our policies, procedures, and practices.”
Prohibited Use of Al Tools
As this guidance describes the benefits of Al in education, the educational community also recognizes
that risks must be addressed. Below are the prohibited uses of Al tools and the measures schools and
districts should take to mitigate the associated risks:
Student Learning
* Bullying/harassment: Using Al tools to manipulate media to impersonate others for bullying,
harassment, or any form of intimidation is strictly prohibited. All users are expected to employ
these tools solely for educational purposes, upholding values of respect, inclusivity, and academic
integrity at all times. Harassment, bullying, and intimidation are defined in Appendix A of WVBE
Policy 4373.
* Overreliance: Dependence on Al tools can decrease human discretion and oversight. Important
nuances and context can be overlooked and accepted. Teachers will clarify if, when, and how Al
tools should be used in their classrooms through discussions and modeling, and teachers and
students are expected to review outputs generated by Al before use.
* Plagiarism and cheating: Students and staff shall not copy from any source, including
generative Al, without prior approval and adequate documentation. Students shall not submit
Al-generated work as their original work. Staff and students must be taught how to properly
cite or acknowledge the use of Al where applicable. Teachers must be clear about when and
how Al tools may be used to complete assignments and restructure assignments to reduce
opportunities for plagiarism by requiring personal context, original arguments, or original data
collection. WVBE Policy 2460 prohibits engaging in plagiarism or reproducing/ repurposing
media without permission.” Additionally, WVBE Policy 2460 requires that students be taught the
ethical and practical implications and consequences of plagiarism.”
® Code.org, COSN, Digital Promise, European EdTech Alliance, Larimore, J, and PACE (2023). Al Guidance for Schools Toolkit. Retrieved
from teachai.org/toolkit. [November 30, 2023].
20 WVBE Policy 4373, Expected Behavior in Safe and Supportive Schools, https://apps.sos.wv.gov/adlaw/csr/readfile.
aspx?Docld=51038&Format=PDF#page=25
21 WVBE Policy 2460, Educational Purpose and Acceptable Use of Electronic Resources, Technologies, and the Internet, https://apps.
sos.wv.gov/adlaw/csr/readfile.aspx?Docld=50142& Format=PDF#page=14
22 WVBE Policy 2460, Educational Purpose and Acceptable Use of Electronic Resources, Technologies, and the Internet, https://apps.
sos.wv.gov/adlaw/csr/readfile.aspx?Docid=50142&Format=PDF#page=16
[ * |
+ Freedom of expression: Section 1 of WVBE Policy 4373 addresses student inquiry & expression.
While free speech is protected, it is important to note this section states “School-sponsored
student publications that are a part of the curriculum are subject to teacher editorial control
and therefore student speech may be regulated in a manner reasonably related to educational
purposes.” #
* Equal access: If an assignment permits the use of Al tools, the tools will be made available to all
students, considering that some may already have access to such resources outside of school.*
* Inappropriate material: It has been noted in the news that with malevolent intent, Al
applications can be “tricked” into creating inappropriate material.” WVBE Policy 2460 prohibits
the inappropriate transmission of any material in violation with federal and state law” as well
as the “viewing, storing, transmitting, or downloading of pornography or sexually suggestive or
sexually explicit material” which Al-generated material would fall under.”
Teacher Support
* Societal Bias: Al tools trained on human data will inherently reflect societal biases in the data.
Risks include reinforcing stereotypes, recommending inappropriate educational interventions,
or making discriminatory evaluations, such as falsely reporting plagiarism by non-native
English speakers. Staff and students will be taught to understand the origin and implications of
societal bias in Al; additionally, Al tools will be evaluated for the accuracy of their training data
and transparency, and humans will review all Al-generated outputs before use.
* Diminishing student and teacher agency and accountability: While generative Al presents
useful assistance to amplify teachers’ capabilities and reduce teacher workload, these
technologies will not be used to supplant the role of human educators in instructing and
nurturing students. The core practices of teaching, mentoring, assessing, and inspiring
learners will remain the teacher's responsibility in the classroom. Al is a tool to augment
human judgment, not replace it. Teachers and staff must review and critically reflect on all Al-
generated content before use, thereby keeping “humans in the loop.’
* Privacy concerns: Al tools will not be used to monitor classrooms for accountability purposes,
such as analyzing teacher-student interactions or tracking teacher movements, which can
infringe on students’ and teachers’ privacy rights and create a surveillance culture.”
23 WVBE Policy 4373, Expected Behavior in Safe and Supportive Schools, https://apps.sos.wv.gov/adlaw/csr/readfile.
aspx?Docid=51038&Format=PDF#page=7
% Code.org, COSN, Digital Promise, European EdTech Alliance, Larimore, J, and PACE (2023). Al Guidance for Schools Toolkit. Retrieved
from http://teachai.org/toolkit. [November 30, 2023].
> Candanosa, R. M. (2023, November 1). Al image generators can be tricked into making NSFW content. The Hub. https://hubjhu.
edu/2023/11/01/nsfw-ai/.
76 WVBE Policy 2460, Educational Purpose and Acceptable Use of Electronic Resources, Technologies, and the Internet,
https://apps.sos.wv.gov/adlaw/csr/readfile.aspx?Docld=50142&Format=PDF#page=13
277 WVBE Policy 2460, Educational Purpose and Acceptable Use of Electronic Resources, Technologies, and the Internet,
https://apps.sos.wv.gov/adlaw/csr/readfile.aspx?Docld=50142& Format=PD F#page=10
78 U.S. Department of Education, Office of Educational Technology, Artificial Intelligence and Future of Teaching and Learning: Insights
and Recommendations, Washington, DC, 2023.
79 Code.org, COSN, Digital Promise, European EdTech Alliance, Larimore, J, and PACE (2023). Al Guidance for Schools Toolkit. Retrieved
from http://teachai.org/toolkit. [November 30, 2023].
[= |
School Management and Operations
* Compromising Privacy: The county school district or school will not use Al in ways that
compromise teacher or student privacy or lead to unauthorized data collection, as this violates
privacy laws and our system’s ethical principles. WVBE Policy 2460 requires that counties are
responsible for ensuring that COPPA, CIPA, and FERBA are not violated.” See the Security,
Privacy, and Safety section for more information.
* Noncompliance with Existing Policies: We will evaluate Al tools for compliance with all relevant
policies and regulations, such as privacy laws and ethical principles. We will review the terms
and conditions for all Al tools to review if/how personal information is used to ensure that
personal data remains confidential and isn’t misused.”
30 WVBE Palicy 2460, Educational Purpose and Acceptable Use of Electronic Resources, Technologies, and the Internet.
a Codex org, COSN, Digital Promise, European EdTech Alliance, Larimore, J, and PACE. (2023). Al Guidance for Schools Toolkit. Retrieved
from http://teachai.org/toolkit. [November 30, 2023].
Protecting Student Privacy and Safety
Security, Privacy, and Safety
Al is a technology tool similar to other educational/instructional
technologies. Its powerful implications and novel uses will
require more time and experience to fully integrate responsibly.
However, planning for the use of Al should be approached
in a manner similar to planning for other educational
technologies. District and school staff should be able to clearly
articulate the needs and uses for Al tools, plan for systematic
implementations, monitor uses and impacts, and adjust plans
as needed in response to outcomes and user feedback. As part
of these planning processes, student and staff privacy must be
considered at every step along the way to ensure safety and
security.
Al systems, especially those used in education, require extensive
data to operate efficiently. In an educational setting, these data
could include sensitive information about students like learning
patterns, academic achievements, and personal details. The
foremost ethical concern is student privacy, and districts need
to ensure that such sensitive data is handled with utmost care.
Obtaining parental consent Is crucial, but it is also important
to recognize that even with consent, using identifiable data in
public Al models is not advisable. Any data information inputted
into the Al model, including prompts, has the potential to be
incorporated into the model's future iterations and potentially
Best practice guidance from the
National Forum on Education
Statistics may be helpful for
school and district staff when
planning for the implementation
of new technologies, including
Al, and for protecting student
privacy.
Forum Guide to Cybersecurity:
Safeguarding Your Data
https://nces.ed.gov/forum
cybersecurity.asp
Forum Guide to Technology
Management in Education
https://nces.ed.gov/forum/tec
govern_planning.asp
Forum Guide to Education Data
Privacy
https://nces.ed.gov/forum
pub 2016096.asp
shared with other users. Hence, strict policies, consideration, and discretion are essential when
integrating Al in educational settings to safeguard against any privacy breaches or misuse of student
data.
Schools should implement reasonable security measures to secure Al technologies against
unauthorized access and misuse. These measures may include (1) cataloging the tools used, their
purposes/functions, and the information required (e.g, information about individuals, prompts
or questions, aggregate data); (2) establishing rules or criteria for who can use Al tools for what
purposes and/or creating school-specific guidelines for use of Al tools; and (3) maintaining up-to-date
information about the technical details and security implications of the tools in use. All Al systems
deployed within the school should be evaluated for compliance with relevant laws and regulations,
including those related to data protection, privacy, and students’ online safety. Schools and districts
should also ensure that staff are adequately trained for how to securely and successfully use Al tools
from both cybersecurity and instructional perspectives.
Staff and students are prohibited from entering confidential or personally identifiable information into
unauthorized Al tools, such as those without approved data privacy agreements. Sharing confidential
or personal data with an Al system could violate privacy if not properly authorized (with appropriate
consent, as needed) or if information is not provided via approved procedures.
[|
Evaluating Al Products
Common Sense Media has developed an Al Ratings System which provides schools and districts a
framework “designed to assess the safety, transparency, ethical use, and impact of Al products.’”
The joliowmn resources are also provided to inform ethical Al software procurement:
Emerging Technology Adoption Framework
The Ethical Framework for Al in Education
SHA Education Technology Industry's Principles for the Future of Al in Education
EdSAFE Al SAFE Benchmarks
Special Consideration: Student Age
Every technology has a set of terms and conditions which must be reviewed. When considering the use
of generative Al technologies — for example, ChatGPT, with students under the age of 18 - several key
considerations should be addressed:
- First, explicit parental/guardian permission must be obtained for students under 18, ensuring
that parents/guardians are fully informed about the nature, capabilities, and limitations of the
Al technology, as well as the data privacy and security measures in place.
It should be noted that specialists in the field of classroom Al have advised that students
should ideally be at least 13 years old to utilize Al technology.* Nevertheless, acquiring Al
literacy and developing a comprehension of the technology remains crucial for learners of all
ages in our increasingly digital world.*
For students under the age of 13, special attention is needed due to stricter laws like the
Children’s Online Privacy Protection Act (COPPA). Additionally, the use of Al should be closely
monitored by educators to ensure that the content and interaction are age-appropriate,
respectful of privacy, and aligned with educational goals.
WVBE Policy 2520.14 notes that technology tools must be age-appropriate, specifically when
used with the youngest learners.*®
WVBE Policy 2520.14 notes that older students must be instructed in using modern technologies
in order to prepare them for college or career.”
Sample Considerations for Existing School and District Policies
Guidelines should be incorporated into existing district and school policies. Below are examples
of language relevant to responsible use policies, privacy policies, and academic integrity policies.
32 Common Sense Media, “Common Sense Media Announces Framework for First-of-Its-Kind Al Ratings System,” September 15, 2023,
https://www.commonsensemedia.org/aiframework
33 Code.org, COSN, Digital Promise, European EdTech Alliance, Larimore, J, and PACE. (2023). Al Guidance for Schools Toolkit. Retrieved
from http://teachai.org/toolkit. [November 30, 2023].
3 “UNESCO Recommends Age Limit of 13 for Classroom Antinee item genGe Use.” washington Examiner, September 7, 2023. https://
2 Klein, A. “Al Literacy, Explained” Education Week, May 10, 2023. https: ‘iammnczcucel apliedinologuial: literacy-explained/2023/05
36 WVBE Policy 2520.14, West Virginia College- and Career-Readiness Standards for Technology and Computer Science, https://apps.sos.
wv.gov/adlaw/csr/readfile.aspx?Docid=50990 &Format=PDF#page=6
37 WBE Policy 2520.14, West Virginia College- and Career-Readiness Standards for Technology and Computer Science, https://apps.sos.
wv.gov/adlaw/csr/readfile.aspx?Docid=50990 &Format=PDF#page=12
| = |
These policies should be developed in accordance with the county school district’s and/or school’s
established policy development process.
In creating district or school guidance or addendums to existing policies, it is recommended that you:
Use language that’s clear and familiar to educators, administrators, and students.
Engage local educators, parents, students, and community members to gather feedback and
insights.
- Account for the available technological infrastructure, like internet access and device
availability.
Ensure policies account for the training needs of educators to implement new guidelines
effectively.
Below are examples for illustrative purposes and should be customized to the needs of your district
and/or school.
Responsible Use Policy: Al Tools & Systems
Al Output Review: Always review and critically assess outputs from Al tools before submission
or dissemination. Staff and students should never rely solely on Al-generated content without
review.
Bias and Misinformation: Be aware that Al-generated content may possess biases or
inaccuracies. Always verify Al-produced results using trusted sources before considering them
in academic work.
Safety and Respect: Users must not use Al tools to create or propagate harmful, misleading, or
inappropriate content. (Note: This may also be added to a student code of conduct or bullying/
harassment policy.)
Transparency: Any use of Al to aid assignments, projects, or research must be declared.
Usage: Al tools will be used for educational purposes only. Misuse or malicious use of Al
technologies will lead to disciplinary action.
Privacy Policy: Al & Data Collection
Data Collection: Parents, guardians, and students will be informed of specific data collection
initiatives, and where applicable, consent will be sought. All Al-driven data collection will
adhere to local data protection regulations and best practices.
Third-Party Al Tools: Schools may develop an approved list of Al tools which should always be
consulted. Unauthorized Al tools might not adhere to data privacy standards.
Personal Information: Staff and students should never input personal, sensitive, or confidential
data into any Al system without prior authorization, including any data related to student
education records.
Academic Integrity Policy: Al Assistance
Assessments: Al tools may be used as a tutor or studying assistant to prepare for assessments,
such as exams or quizzes, but not in the context of completing exams or quizzes unless
explicitly stated.
Assignments: Teachers are responsible for clarifying appropriate or prohibited uses of Al
tools. Teachers might allow the limited use of generative Al on entire assignments or parts
of assignments. They should articulate why they do not allow its use in other assignments or
parts of assignments.
[ = |
* Bias and Critical Thinking: Teachers and students alike should critically evaluate Al-generated
content for potential biases or inaccuracies and understand the limitations of Al and the
importance of cross-referencing with trusted sources.
* Citations: Any Al-generated content used in assignments must be appropriately cited; its use
must be disclosed and explained. As part of the disclosure, students may choose to cite their
use of an Al system using one of the following resources:
» MLA Style - Generative Al
» APA Style - ChatGPT
» Chicago Style - Generative Al
* Plagiarism: Al tools may be used for brainstorming or preliminary research, but using Al to
generate answers or complete assignments without proper citation or passing off Al-generated
content as one’s own is considered plagiarism.
¢ Use of Al Detection Tools: At present, technologies that claim to detect content developed by
generative Al are not sufficiently accurate to make reliable determinations of cheating and
plagiarism. Therefore, while some teachers might use such systems to inform the feedback they
provide to students about improving their writing, we discourage reliance on these systems to
determine responsibility in cases where plagiarism is suspected.*
Communicating with the Community
Communication is vital to successfully integrating artificial intelligence (Al) into school settings and
engaging with parents and guardians is a key step in connecting families with the county school
district’s vision and recommendations for Al use in schools. This communication ensures transparency,
providing parents/guardians with a clear understanding of how Al tools will be used and the benefits
they potentially offer students. It also fosters collaboration where families can voice their opinions
and concerns, thereby contributing to a more comprehensive and well-rounded strategy that
harnesses the potential of Al.
Within the WVDE Canvas Course, WVDE Professional Learning Resource for Artificial Intelligence, district
administrators will find templates for communication with communities, families, educators, and
students. Instructions on accessing Canvas resources can be found in Appendix 7.
Supporting Al in Instruction
Given the novel nature of artificial intelligence (Al) in the educational landscape, it is important
to consider incorporating Al-focused content into all professional development opportunities for
educators. The rapid advancement and integration of Al technologies necessitates that teachers are
not only familiar with these tools but are also comfortable in leveraging those selected by the county
school district to enhance teaching and learning.
Professional development opportunities should therefore include content on the ethical use of Al,
understanding its capabilities and limitations, and integrating Al tools into classroom instructional
design. This approach will ensure that educators are equipped to navigate the challenges posed by Al,
38 Code.org, COSN, Digital Promise, European EdTech Alliance, Larimore, J, and PACE (2023). Al Guidance for Schools Toolkit. Retrieved
from http://teachai.org/toolkit. [November 30, 2023].
adapt to its developing role in education, and harness its potential to improve student outcomes. By
prioritizing Al literacy in professional development, educators can stay ahead of the curve, fostering a
future-ready educational setting that benefits both educators and students.
Within the WVDE Canvas Course, WVDE Professional Learning Resource for Artificial Intelligence,
district administrators will find resources to support providing professional development to educators.
Instructions on accessing Canvas resources can be found in Appendix 1.
Moving Forward
The West Virginia Board of Education lists as its goals the intent to “Provide a high-quality learning
system that:
Encourages a lifelong pursuit of knowledge and skills
Promotes a culture of responsibility, personal well-being, and community engagement
Responds to workforce and economic demands”
Further, WVBE Policy 2460, Educational Purpose and Acceptable Use of Electronic Resources,
Technologies, and the Internet, focuses on the importance of an “...effective public education system
which develops students who are globally aware, engaged with their communities, and capable of
managing their lives and careers to succeed in a digital world.’
As districts, schools, and educators move forward with incorporating Al into instructional practice, it
is the expectation of the WVDE that all stakeholders will use this guidance and will provide feedback
on the guidance and accompanying Canvas resource site. This process will lead to a common goal of
bettering the guidance for all West Virginia county school districts and their students.
3 WVBE Paley 2460, Educational Purpose and Acceptable Use of Electronic Resources, Technologies, and the Internet.
References
Note: The WVDE is a Participating Government Agency in the work of TeachAl. This guidance was
informed by the work of TeachAl! (TeachAl.org) which is licensed under a Creative Commons license
(CC BY-NC-SA 4.0). This work was adapted and modified under the license, and as such, this work is
published under the same license, allowing the work to be shared and adapted for non-commercial
purposes.
California Department of Education. (2023). Learning With Al, MI, Learning About Al, Retrieved from https://
a — romote%20ethical%20use%200 %20technolo , [November 30, 2023].
Candanosa, R. M. (2023, November 1). Al image generators can be tricked into making NSFW content.
The Hub. https://hubjhu.edu/2023/11/01/nsfw-ai/
Code.org, COSN, Digital Promise, European EdTech Alliance, Larimore, J., and PACE. (2023). Al Guidance
for Schools Toolkit. Retrieved from http://teachai.org/toolkit. [November 30, 2023].
Common Sense Media. (2023, September 15). Common Sense Media Announces Framework for
First-of-Its-Kind Al Ratings System [Press Release]. Common Sense Media.
https://www.commonsensemedia.org/aiframework.
Gallagher, H. A., & Cottingham, B. W. (2023, June). The urgent need to update district policies on student
use of artificial intelligence i in education [Commentary]. Policy Analysis for California Education.
intelligence- -paucaion
Goldsberry, J. (2023, September 7). UNESCO recommends age limit of 13 for classroom artificial
intelligence use. Washington Examiner. https://www.washingtonexaminer.com/news/education/
unesco-age-limit-classroom-ai-use.
Hoffman, R. (2023). Impromptu: Amplifying our Humanity Through Al. Dallepedia.
International Center for Academic Integrity [ICAI]. (2021). The Fundamental Values of Academic
Integrity. (3rd ed). https://academicintegrity.org/about/values.
Klein, A. “Al Literacy, Explained.” Education Week, May 10, 2023. hitps://www.edweek.org/technology/ai-
literacy-explained/2023/05.
OpenAl. (2023). ChatGPT (September 25 Version) [Large language modell]. https://chat.openai.com.
Oregon Department of Education. (2023). Generative Artificial Intelligence (Al) in K-12 Classrooms.
Retrieved from https://www.oregon.gov/ode/educator-resources/teachingcontent/Documents/
ODE Generative Artificial Intelligence (Al) in K-12 Classrooms 2023.pdf. [November 16, 2023].
[ = |
Puentedura, R. (2006). Transformation, technology, and education [Blog post]. Retrieved from
http://hippasus.com/resources/tte/.
U.S. Department of Education, Office of Educational Technology, Artificial Intelligence and Future of
Teaching and Learning: Insights and Recommendations, Washington, D.C., 2023.
West Virginia Board of Education. (2018). Policy 2460: Educational Purpose and Acceptable Use of
Electronic Resources, Technologies, and the Internet. Title 126, Series 41. Retrieved from:
https://apps.sos.wv.gov/adlaw/csr/readfile.aspx?Docid=50142&Format=PDF.
West Virginia Board of Education. (2018). Policy 2520.14: West Virginia College- and Career-Readiness
Standards for Technology and Computer Science. Title 126, Series 44. Retrieved from:
https://apps.sos.wv.gov/adlaw/csr/readfile.aspx?Docid=50990&Format=PDF
West Virginia Board of Education. (2019). Policy 4373: Expected Behavior in Safe and Supportive
Environments. Title 126, Series 99. Retrieved from: https://apps.sos.wv.gov/adlaw/csr/readfile.
aspx?Docld=51038&Format=PDF.
West Virginia Board of Education. (2023, October 19). State Board of Education Goals Statement.
West Virginia Department of Education. https://wvde.us/state-board-of-education/.
APPENDICES
Appendix 1 - Canvas Self-Enrolling Resource Directory
All West Virginia educators have access to Canvas, an online learning platform. Educators can
customize their Canvas dashboards by enrolling in grade-level, course WVCCR Standards sites, or
resource sites. For enrollment links, download the Self-Enrolling Resource Directory to your Canvas
dashboard.
1. Log into Canvas: https://wvde.instructure.com.
2. Use your single-sign-on credentials to access Canvas.
3. If this is your first time logging into Canvas, read and agree to the Acceptable Use Policy.
4, Go to RESOURCES from the menu on the left, and choose Self-Enrolling Resource Directory
oy Resources
®@
DG} Immersive Reader
Account
Directory
.
Dashboard
West Virginia Department of Education
are available for educators to customize their Canvas dashboards. Click the links provided to open and view
© analso place the resource on your Canvas dashboard permanently using the self-enrolling links provided
WVCCR Standard Sites
Catalog Search
COVID-19 Canvas Resources
|| Tips for teaching and learning online
5. Click + Join this Course to place Self-Enrolling Resource Directory permanently on your Canvas
dashboard.
oy = _Self-Enrolling Resource Directory O33 Immersive Reader
ia) , ,
& Home Self-Enrolling Resource Directory tls View Course Stream
Account
+ Join this Course
@
Dashboard Conia
i E
Nothing for the next week
West Virginia Department of Education
Welcome!
The following sites are available for educators to customize their Canvas dashboards.
Click the links provided to open and view the resource. You can also place the
resource on your Canvas dashboard permanently using the self-enrolling links
provided.
History
6. Scroll down to find/open the standards, sites, and resources you need. Click + Join this Course to
place those resource permanently on your dashboard.
| |
Appendix 2 - Glossary
Algorithm: A set of formulas and/or instructions given to a computer for it to complete a task.
Artificial Intelligence (Al): The field of computing that aims to create machines or software capable of
intelligent behavior. Al systems can perform tasks that typically require human intelligence, such as
visual perception, speech recognition, decision-making, and language translation.
Al Literacy: The ability to use and interact with Al systems effectively, efficiently, and responsibly.
Bias in Al: The systematic prevalence of untrue and/or harmful information that leads to unfair,
inaccurate, or discriminatory outcomes in the decision-making process or results of an Al system. It
can manifest directly or indirectly, stemming from the data used to train the system or the design of
the algorithm itself.
Data: Text or numeric information that can be stored, processed, or analyzed by a computer.
Data Privacy: The aspect of handling, processing, and storing personal and sensitive data with
confidentiality and security. In Al, this involves ensuring that data used for training and operating Al
systems Is protected from unauthorized access and misuse.
Deep Learning: Deep learning is an advanced type of machine learning. It studies numerous examples
(like images or speech) and translates them into layers of numbers and statistical models, often
referred to as ‘neural networks’, to capture complex patterns in data. These neural networks mimic the
way our brain works. Deep learning is particularly effective for tasks like image and speech recognition.
Ethics in Al: The moral principles and guidelines that govern the development and use of Al
technologies. This includes considerations of fairness, transparency, accountability, and the impact of
Al on society and individuals.
Generative Al: A type of Al that specializes in creating new content, such as text, images, and audio, by
learning from existing data. It can generate realistic and coherent outputs that mimic original data sources.
Large Language Model (LLM): Complex statistical models that use billions of variables to capture the
characteristics and content of language across billions of sentences. LLMs can be used to study how
the English language is written across different contexts and use that understanding to write new text
(e.g, answering questions, creating summaries or lists).
Machine Learning (ML): The ability of a machine to predict outcomes without someone giving it exact
instructions. ML involves complex statistical models to make predictions (i.e., learning the connections
between variables).
Model: In Al, a model refers to the specific trained algorithm capable of performing tasks such as
prediction, classification, or content generation. Models are trained using datasets and refined until
they achieve the desired level of accuracy.
Natural Language Processing (NLP): A branch of Al that focuses on the interaction between computers
[|
and humans through natural language. NLP involves the interpretation, understanding, and generation
of human language by Al systems.
Neural Networks: Computational models that are inspired by the human brain's structure and
function. These networks are composed of interconnected nodes (similar to neurons) and are used to
model complex patterns in data for tasks such as classification and prediction.
Prompt: A question or task provided to an Al tool that is the basis for the action it should perform.
A prompt generally contains detailed information related to what the computer should do and any
constraints under which it should operate.
Training Data: The dataset used to train Al models. This data provides the examples and experiences
that Al systems use to learn how to perform tasks, make predictions, or generate content. The quality
and diversity of training data significantly influence the performance of Al models.*°
“0 Adapted from the results of the output from this prompt: “Please assist me in developing a starting list of vocabulary that an
educator would need to know in order to understand the basics of generative Al” prompt. ChatGPT-4, 7 April. version, OpenAl, 21
Nov. 2023, http://chat.openai.com/chat.
“Juawuleye ydadu0d jo AyNoWYIp eu
0} paynqijUOD JO SUO!ENSIP pasned arey
Aew | $0 asn ayi yodiym ul Shem ssassy
“sdny eq YI9}-MO] JO YIO}-OU JO} UR]d
‘S]00} |V DyI9eds YIM sulsesua SedUaadxa ‘(Iv Aq Ajauua paje}dwuos aq youued
JIU] UO JIeQPaaJ JUSPNIS 104 }SV xx lv SuIsn squlod Aay Sed.0JUI9 4} BNSO]D UOSSE] 104 UEId Aay} Jeu) OS paidepe/pausisap sjuawusisse
‘seap! aleiaued Yayzes) JayJaSOe paplone aq Jou pynoys |v
01 |v Sulsn (s)se} 8o;]9e1d Juspuadapu! Us!Isaq ‘payeaid-ly JOU sem ued UOSsa] JIN} aUL
‘asimiadns ued noA ‘S]OO} |v Suisn pue Suioajas ul pazuoud
‘Sp9ou Suluses] ,SjuapNys ya, 4 ! p Peto
1nof 0} pans Janjag ave Tey sjeuiayeU ye} SOIANDe BdIDeId poyoddns-|y asedaid pue ue}d uaaq ave Sulag-]jam puke Ajajes uapnys
yeuolpniysul Sulgnpodd ul ainyny ayy ‘UONINYSU! SULINP ‘asn yeaiyja pue Ajusaqul Jlwapese
UI PaYy!POW aq Ue S]OO} |y 0} papiAcid SUIPUeISIAPUN S]UapPNys SSasse 0} $]OO} |V AjIUSP|, JO aunyjnd e adUeApe 0} pasn SI |y
sidwoud Yyd!yM ul SAeM UO DAaYEY
“SJOAISAICD JO SIBQWAW
Awe} 0} SSausoJd JUapNs aJeIUNWWOD,
‘saianoe Juapms pue yndul }euononjsul “pasn 100} | Ydea JO} paiapisuod uaagq
‘seolqyoeud JO Suluueyd 84] NPuUOd 0} papaeu $]Oo} pure ‘sadinosal aney ly Suisn Jo saSuayjeyd pue SSH OUL
yeuolonsysul aulynos INOA Jo Wed se s}00} ‘sjeluayew sulwioddns Jo ‘|v suisn ‘Jsi] jellul Ue a}eaID : :
IV lads Jo asn panuljuos ay} ayenyenq ‘SUIUIYY JID pue asn ayqisuodsal
Ndjno ayy jo Aye]d JeEuoNINAYsU! ayy ayenyena pue 0 Siseydwa yum ‘uo!anSU! OUI
UOIINAYSU] JOY SUIJOPOW JOJ Salsojeue JO Sa]dwexa pa}eisuas-|y asedald payeiodiooul Ajssajweas Bulag S| A0e1831) IV
‘SalqJEPOW SuUIUed]
SNOLEA YUM SJUAPN}S 0} ]]P{S/JdauOD ay} eyesSUOWAapP
‘(ayqeaijdde 41) 0} pasn aq ued 100} |y Ue MOY eol}DeId JO/pue Ue}
$]00} |'¥ SUISN UOSS9] JX9U BY} O} UO!ISURLL “ly Suisn
sne ° ° K 3S ‘(aUel]dWOd 104 a]qisuodsal aie syasn
‘sindjno paslsap uleyqo 0} Vy YM SNe} 9q OF SHIPS PUS UONCULOJU! AB 94} 9Z|UeSIO — JUeI]CWOD Ydy44 JOU ae SaAjasway}
“SPB9U BUILILS] SSBAIP JAU10
JO salujiqesip uM Ssjuapnis 0} ajqissea0e
ase ASN JEUONINISU! JO} PAYNUAP! $]OOI [Wax
SUOIDEIAIU! AANNPOId pue aAIDaye Japow ‘Iv suisn Aye JO} payxdayo $]00} |'¥) ‘ADeAUG JUapNys 1De}0/1d 0}
; -a]qnop ae yey] SAWODINO ajqeunseaw ‘Vea}d dojanaq suoljejnsay pue saldijod sulsixe YUM
‘uolnquye Jadoid als 0} aed Sule} ‘S]OO} : juawusiye Ul pasn sulaq ase S]O0} |V
|v $0 aSn jedIUJa pue ajqisuodsal japow ye 0} 8]q!SSe53e
S| pue uoluaye Sjuapnys sainyded yey Aem e ul “Aypiqeljas yenjoes JUSIDLUNS ue ‘SUIaDUOD
‘yoeqpaal apiAoid pue saiianoe adipeud yelayew JUasaid 0} pasn aq ued }eY} S]OO} | Ayiquap| yedIuja ‘Saseiq JO} payenyera AjyoI)dxe usaq
peuoddns-|y sjuapnis asimiadns,, SAY BSN JEUOIDNIYSU! JO} PEULNUSP! $]00} [V7
“sorAjeue
‘uolqonNs4sSul Jsn[pe pue IV SUISN aspaymouy JOlUd SjuapNys Ajle]D pue Ayuap], *Saldi]od $91UISIP INOA YUM JUAaIsISUOD ae
un |S] 9SN JEUOIPNIISU! JOJ PAY!Uap! S}OO}
lV Sulsn sulpuesiapUN SjUapNys ssassy, ‘papaau se sioqensiuimipe ] IPNIYSU! JOJ POY!USP! S] IV
‘UoISNjUuOd S]UapNys O} SuIppe SI JO/pue ‘Saydeod jeuo!aNIISU! ‘Sansea}jod Wo SUOIUIdO ‘yaoejdas
H fl JoUuJEsOVPe |V S}EUIWI}a JO SUIP}OYeos /andul Jayyey “(W]e 7e JI) UOSSa] UAAIS By] Sulu} }OU Yoyednpa sued e Aq uolqonsysul
aplAoid 0} |v sulsn Aq uoNoNsysu! IsNipy JO} $]OO} |¥ Dyldads Sulsn jo AjyiqeyNs ayy ayenjery juawajddns 0} pasn sulaq SI IV
UO!}DNJYSU| JO} Gulu} sas ajqisuodsay
SYOLVINGI AM YOF LSIDIDAHD GISNIGNOD V
SUIUAJe|] pue SUIYIeA] 104 |W SUIS UBM SUOI}E1apISUOD
Michele L. Blatt
West Virginia Superintendent of Schools