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

TL;DR

This paper presents ThemeClouds, an LLM-assisted visualization tool that creates participant-weighted word clouds highlighting thematic concepts in qualitative interview transcripts, improving interpretability over traditional frequency-based methods.

Contribution

Introduces ThemeClouds, a novel LLM-based tool for generating thematic, participant-weighted word clouds that enhance qualitative data analysis.

Findings

ThemeClouds surfaces more actionable insights than traditional frequency clouds.

The approach outperforms topic-modeling baselines like LDA and BERTopic.

The tool offers customizable prompts and visualization parameters for researcher control.

Abstract

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'').