# Word Clouds as Common Voices: LLM-Assisted Visualization of Participant-Weighted Themes in Qualitative Interviews

arXiv: https://arxiv.org/abs/2508.07517 · HTML: https://mlsanity.com/paper/2508.07517/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 24 references that are in the map.
- First posted on arXiv 11 Aug 2025.

## Builds on (most cited first, 7 of 7)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Neural Topic Modeling of Psychotherapy Sessions](https://mlsanity.com/paper/2204.10189/) (2022)
- [COMPASS: Computational Mapping of Patient-Therapist Alliance Strategies with Language Modeling](https://mlsanity.com/paper/2402.14701/) (2024)
- [Psychotherapy AI Companion with Reinforcement Learning Recommendations and Interpretable Policy Dynamics](https://mlsanity.com/paper/2303.09601/) (2023)
- [RACER: An LLM-powered Methodology for Scalable Analysis of Semi-structured Mental Health Interviews](https://mlsanity.com/paper/2402.02656/) (2024)
- [Semantic Word Cloud Representations: Hardness and Approximation Algorithms](https://mlsanity.com/paper/1311.4778/) (2013)

## Abstract (arXiv)

Word clouds are a common way to summarize qualitative interviews, yet traditional frequency-based methods often fail in conversational contexts: they surface filler words, ignore paraphrase, and fragment semantically related ideas. This limits their usefulness in early-stage analysis, when researchers need fast, interpretable overviews of what participant actually said. We introduce ThemeClouds, an open-source visualization tool that uses large language models (LLMs) to generate thematic, participant-weighted word clouds from dialogue transcripts. The system prompts an LLM to identify concept-level themes across a corpus and then counts how many unique participants mention each topic, yielding a visualization grounded in breadth of mention rather than raw term frequency. Researchers can customize prompts and visualization parameters, providing transparency and control. Using interviews from a user study comparing five recording-device configurations (31 participants; 155 transcripts, Whisper ASR), our approach surfaces more actionable device concerns than frequency clouds and topic-modeling baselines (e.g., LDA, BERTopic). We discuss design trade-offs for integrating LLM assistance into qualitative workflows, implications for interpretability and researcher agency, and opportunities for interactive analyses such as per-condition contrasts (``diff clouds'').