ScholarMate: A Mixed-Initiative Tool for Qualitative Knowledge Work and Information Sensemaking

TL;DR

ScholarMate addresses the challenge of qualitative sensemaking over large text corpora by uniting mixed-initiative AI assistance with human-directed, canvas-based organization. The system provides AI-driven theme suggestions, multi-level summarization, and evidence-grounded theme naming within a non-linear workspace that preserves traceability to source documents. Through a pilot and a use-case study on 24 papers, it demonstrates that balancing automation with direct manipulation improves efficiency and interpretability without sacrificing critical engagement. The work advances human-AI collaboration in demanding sensemaking tasks by emphasizing transparency, traceability, and ethical use, with broad implications for qualitative research workflows and knowledge management.

Abstract

Synthesizing knowledge from large document collections is a critical yet increasingly complex aspect of qualitative research and knowledge work. While AI offers automation potential, effectively integrating it into human-centric sensemaking workflows remains challenging. We present ScholarMate, an interactive system designed to augment qualitative analysis by unifying AI assistance with human oversight. ScholarMate enables researchers to dynamically arrange and interact with text snippets on a non-linear canvas, leveraging AI for theme suggestions, multi-level summarization, and evidence-based theme naming, while ensuring transparency through traceability to source documents. Initial pilot studies indicated that users value this mixed-initiative approach, finding the balance between AI suggestions and direct manipulation crucial for maintaining interpretability and trust. We further demonstrate the system's capability through a case study analyzing 24 papers. By balancing automation with human control, ScholarMate enhances efficiency and supports interpretability, offering a valuable approach for productive human-AI collaboration in demanding sensemaking tasks common in knowledge work.