Interactive Visualizations of Word Embeddings for K-12 Students

Source publication / research team or educational organization described in paper

Not specified in extracted text

Researchers, educators, instructors, or facilitators as described in the source publication

• In-school (K-12)

Classroom, course, or resource-based AI education activity

Not specified in extracted text

Interactive Visualizations of Word Embeddings for K-12 Students Saptarashmi Bandyopadhyay1, Jason Xu2, Neel Pawar2, David Touretzky2 1University of Maryland, College Park, College Par; s more intuitive. We include a series of experiments teachers can use to help K-12 students appreciate the strengths and limitations of this representation. Introduction Embeddings are low dimensional representa

NLP / text classification

• Teacher readiness, time, support, and classroom integration may affect implementation quality.
• Use with minors requires attention to privacy, consent, data minimization, and adult supervision.

K-12

Mixed or not explicitly specified; infer from target learner group and intervention design.

Varies by intervention; not specified unless the paper explicitly describes prerequisites.

• Document the AI education intervention, course, tool, or resource described in the source publication.
• Extract the learner context, AI role, pedagogy, outcomes, and constraints for AAB registry comparison.
• Word embeddings, which represent words as dense feature vectors, are widely used in natural language processing.

• Support AAB comparison across AI literacy, AI education, teacher training, higher education, and workforce contexts.
• Capture evidence maturity, transferability, and limitations rather than treating the publication as product endorsement.

• Not an AAB endorsement of the tool, curriculum, provider, or result.
• Not a direct replication record unless the source paper reports implementation details sufficient for replication.

NLP / text classification

Language context discussed in source publication

• Learning object / concept model

• Primary interaction pattern inferred from publication: Learning tool / resource design, Teacher professional development.
• AI capability focus: NLP / text classification.

• Use age-appropriate framing and teacher/facilitator oversight for any classroom deployment.

• Review the publication’s reported context, learner group, AI tool or curriculum, implementation process, and outcome evidence.
• Map the case to AAB registry fields for comparison across educational levels and AI capability types.
• Use the source publication and PDF for any manual verification before public registry release.

• Human educators/researchers remain responsible for instructional design, supervision, interpretation, and ethical safeguards.
• AI systems or AI concepts provide the learning object, support tool, evaluator, simulator, or automation context depending on the paper.

• Instructional / curriculum-based learning
• Registry extraction emphasizes explicit learning goals, observed outcomes, constraints, and safety limitations.

• Teacher readiness, time, support, and classroom integration may affect implementation quality.
• Use with minors requires attention to privacy, consent, data minimization, and adult supervision.

• Case classified under: Published empirical study.
• Pedagogical pattern: Instructional / curriculum-based learning.
• Any additional adaptations should be verified against the full paper before public-facing publication.

• Engagement evidence should be interpreted according to the source paper’s reported method and sample.
• In their seminal paper on word2vec, Mikolov and colleagues showed that a feature space created by training a word pre- diction network on a large text corpus will encode semantic information that supports analogy by vector arithmetic, e.g., “king” minus “man” plus “woman” equals “queen”.

• In their seminal paper on word2vec, Mikolov and colleagues showed that a feature space created by training a word pre- diction network on a large text corpus will encode semantic information that supports analogy by vector arithmetic, e.g., “king” minus “man” plus “woman” equals “queen”.

Word embeddings, which represent words as dense feature vectors, are widely used in natural language processing. In their seminal paper on word2vec, Mikolov and colleagues showed that a feature space created by training a word pre- diction network on a large text corpus will encode semantic information that supports analogy by vector arithmetic, e.g., “king” minus “man” plus “woman” equals “queen”.

• Use age-appropriate framing and teacher/facilitator oversight for any classroom deployment.

• Pre/post or experimental evidence

• Can be used as an AAB evidence record for cross-case comparison, standards drafting, and evidence-maturity mapping.
• Supports identification of recurring patterns in AI literacy, AI education implementation, teacher preparation, assessment, and responsible AI learning.

• Teacher readiness
• Learning tool / resource design
• Teacher professional development
• NLP / text classification

• Completed

K-12

In-school (K-12)

NLP / text classification

Instructional / curriculum-based learning

Low to Medium

Medium

Interactive Visualizations of Word Embeddings for K-12 Students

• Saptarashmi Bandyopadhyay
• Jason Xu
• Neel Pawar
• David Touretzky

Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36 No. 11, EAAI-22

2022

10.1609/aaai.v36i11.21548

https://ojs.aaai.org/index.php/AAAI/article/view/21548

https://ojs.aaai.org/index.php/AAAI/article/view/21548/21297

100_Interactive Visualizations of Word Embeddings for K-12 Students.pdf

8

Word embeddings, which represent words as dense feature vectors, are widely used in natural language processing. In their seminal paper on word2vec, Mikolov and colleagues showed that a feature space created by training a word pre- diction network on a large text corpus will encode semantic information that supports analogy by vector arithmetic, e.g., “king” minus “man” plus “woman” equals “queen”. We describe a new interactive tool for visually exploring word embeddings. Our tool allows users to define semantic dimen- sions by specifying opposed word pairs, e.g., gender is de- fined by pairs such as boy/girl and father/mother, and age by pairs such as father/son and mother/daughter. Words are plot- ted as points in a zoomable and rotatable 3D space, where the third ”residual” dimension encodes distance from the hyper- plane defined by all the opposed word vectors with age and gender subtracted out. Our tool allows users to visualize vec- tor analogies, drawing the vector from “king” to “man” and a parallel vector from “woman” to “king-man+woman”, which is closest to “queen”. Visually browsing the embedding space and experimenting with this tool can make word embeddings more intuitive. We include a series of experiments teachers can use to help K-12 students appreciate the strengths and limitations of this representation.

• In-school (K-12)

• Teacher readiness, time, support, and classroom integration may affect implementation quality.
• Use with minors requires attention to privacy, consent, data minimization, and adult supervision.

Not specified in extracted text unless noted in duration field.

Requires educators/researchers/facilitators with sufficient AI literacy and pedagogy knowledge for the target learners.

Infrastructure depends on AI tool type, learner devices, data access, and institutional policy context.

High

• duration

This entry was automatically extracted from the PDF text and manifest metadata. Fields should be manually verified before public registry publication, especially group size, location, duration, and outcome claims.