Word2Vec4Kids: Interactive Challenges to Introduce Middle School Students to Word Embeddings

• DOI: 10.1609/aaai.v39i28.35197
• Publication Date: 2025-04-11T14:40:09Z
• Authors: Nathan Wiatrek; Yash Verma; Fred Martin

As Artificial Intelligence (AI) continues to integrate into more aspects of society, equipping younger generations with foundational AI knowledge becomes increasingly critical. This paper presents Word2Vec4Kids (W2V4K), an interactive application designed familiarize middle school students word embeddings, a key aspect Natural Language Processing (NLP). W2V4K leverages the Word2Vec model, allowing explore associations, similarity, and vector arithmetic through engaging game modes. The was tested 38 aged 11-14 at Science Technology Engineering Math (STEM)-focused charter school. Data were collected on students' interactions application, including screen recordings, audio, survey responses. Results demonstrated that effectively introduces NLP concepts students. Qualitative observations revealed high levels engagement expressing excitement curiosity about relationships. they progressed modes, showed increasing confidence in predicting brainstorming relevant words, connecting real-world applications. Quantitative data from post-interaction surveys indicated positive learning outcomes 44.5% achieving perfect scores concept-related items. Additionally, ability critically think language representation. study suggests provides effective method for introducing students, contributing broader goal enhancing literacy among generations.