# Thematic and Task-Based Categorization of K-12 GenAI Usages with Hierarchical Topic Modeling

arXiv: https://arxiv.org/abs/2508.09997 · HTML: https://mlsanity.com/paper/2508.09997/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 48 references that are in the map.
- First posted on arXiv 1 Aug 2025.

## Builds on (most cited first, 12 of 12)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [Probabilistic Latent Semantic Analysis](https://mlsanity.com/paper/1301.6705/) (2013)
- [Unveiling the Implicit Toxicity in Large Language Models](https://mlsanity.com/paper/2311.17391/) (2023)
- [Prompting Large Language Models for Topic Modeling](https://mlsanity.com/paper/2312.09693/) (2023)
- [Towards LLM-based Autograding for Short Textual Answers](https://mlsanity.com/paper/2309.11508/) (2023)
- [What is in a Text-to-Image Prompt: The Potential of Stable Diffusion in Visual Arts Education](https://mlsanity.com/paper/2301.01902/) (2023)
- [Constructing Dreams using Generative AI](https://mlsanity.com/paper/2305.12013/) (2023)
- [How Students (Really) Use ChatGPT: Uncovering Experiences Among Undergraduate Students](https://mlsanity.com/paper/2505.24126/) (2025)
- [Topic Modeling based on Keywords and Context](https://mlsanity.com/paper/1710.02650/) (2017)
- [Topic Modeling with Fine-tuning LLMs and Bag of Sentences](https://mlsanity.com/paper/2408.03099/) (2024)
- [The Impact of AI-Driven Tools on Student Writing Development: A Case Study From The CGScholar AI Helper Project](https://mlsanity.com/paper/2501.08473/) (2025)

## Abstract (arXiv)

We analyze anonymous interaction data of minors in class-rooms spanning several months, schools, and subjects employing a novel, simple topic modeling approach. Specifically, we categorize more than 17,000 messages generated by students, teachers, and ChatGPT in two dimensions: content (such as nature and people) and tasks (such as writing and explaining). Our hierarchical categorization done separately for each dimension includes exemplary prompts, and provides both a high-level overview as well as tangible insights. Prior works mostly lack a content or thematic categorization. While task categorizations are more prevalent in education, most have not been supported by real-world data for K-12. In turn, it is not surprising that our analysis yielded a number of novel applications. In deriving these insights, we found that many of the well-established classical and emerging computational methods, i.e., topic modeling, for analysis of large amounts of texts underperform, leading us to directly apply state-of-the-art LLMs with adequate pre-processing to achieve hierarchical topic structures with better human alignment through explicit instructions than prior approaches. Our findings support fellow researchers, teachers and students in enriching the usage of GenAI, while our discussion also highlights a number of concerns and open questions for future research.