This paper explores the potential role of AI, e.g., large language models (LLMs), in supporting theme development in thematic analysis. While prior applications of AI in qualitative data analysis have focused on supporting coding, we investigate whether LLMs can effectively contribute as collaborators in the more abstract and conceptual phases of qualitative analysis, specifically theme development. Despite growing interest in AI as a collaborator in theme development, there is limited empirical evidence on designing AI-assisted tools while supporting user autonomy and understanding researcher interaction with AI-assisted theme development. To address this gap, we designed ThemeViz, an interactive system that uses GPT-4 to generate and visualize multiple versions of themes based on user input while allowing researchers to maintain control through manual coding and theme development. Our study examines the effectiveness of this human-AI collaboration approach in iterative theme development and its implications for future designs.

UX research practitioners analyze qualitative data to comprehend users' needs and synthesize design implications for software systems. Collaborating with multiple stakeholders is inevitable for these professionals and adds additional pressure to their already laborious data analysis tasks. In this paper, we investigate how these practitioners' multi-stakeholder collaboration affects their data analysis practices. Specifically, we investigate the challenges qualitative UX research (QUXR) practitioners face, limitations of the current qualitative data analysis (QDA) support tools they use, and design implications for future QDA tools to address the limitations. Through semi-structured interviews combined with diagramming activities with thirteen industry QUXR practitioners, we have revealed that collaboration becomes a bigger challenge than data analysis and that it often leads to (1) preferring simple tools despite the QDA specialized tools' beneficial features and (2) wanting to triangulate their work to convince stakeholders. Finally, we have synthesized these results and suggest design implications for QDA support tools.

Computational notebooks help data analysts analyze and visualize datasets, and share analysis procedures and outputs. However, notebooks typically combine code (e.g., Python scripts), notes, and outputs (e.g., tables, graphs). The combination of disparate materials is known to hinder the comprehension of notebooks, making it difficult for analysts to collaborate with other analysts unfamiliar with the dataset. To mitigate this problem, we introduce ToonNote, a JupyterLab extension that enables the conversion of notebooks into “data comics.” ToonNote provides a simplified view of a Jupyter notebook, highlighting the most important results while supporting interactive and free exploration of the dataset. This paper presents the results of a formative study that motivated the system, its implementation, and an evaluation with 12 users, demonstrating the effectiveness of the produced comics. We discuss how our findings inform the future design of interfaces for computational notebooks and features to support diverse collaborators.