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

2025-04-19

AI Summary

To address low efficiency, weak interpretability, and insufficient trust in large-scale literature knowledge integration for qualitative research, this study proposes a human–AI bidirectionally主导 mixed active learning paradigm and develops an AI-augmented interactive system supporting nonlinear text organization. The system integrates semantic clustering and topic modeling, hierarchical summarization, interactive visualization canvases, and provenance-enhanced knowledge graphs—enabling AI-driven thematic suggestions, multilevel contextual summaries, and entity naming, all fully traceable to original sources. Its key innovation lies in dynamically balancing AI-generated recommendations with researcher-initiated interventions, thereby jointly optimizing analytical efficiency, cognitive controllability, and result interpretability. Empirical evaluation across 24 scholarly papers and user pilot studies demonstrates significant improvements in information integration efficiency, enhanced interpretability, strengthened collaborative trust, and preserved researcher agency.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Humans and AI: Intelligent User Interfaces
• Knowledge Representation and Reasoning: Qualitative Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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 contextual 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.

Problem

• Enhancing qualitative knowledge synthesis from large document collections
• Integrating AI assistance with human oversight in sensemaking workflows
• Balancing automation and human control for interpretable, trustworthy analysis

Innovation

• AI-assisted theme suggestions and summarization
• Non-linear canvas for dynamic text arrangement
• Traceability to ensure transparency and trust