DeepConnect: A Visual Analytics System for Bridging Interdisciplinary Research Collaborations
2026-08-05 • Human-Computer Interaction
Human-Computer Interaction
AI summaryⓘ
The authors created DeepConnect, a tool that helps researchers from different fields find and connect with each other for collaboration. It uses a language model to turn broad project ideas into specific tasks and finds relevant research papers to help users understand each other's work. The system also shows shared and different terms across fields and helps users practice conversations before reaching out. They tested DeepConnect through studies, showing it helps form complementary teams and prepare for successful collaboration.
interdisciplinary researchcollaborator discoverylarge language modelsvisual analyticsresearcher profilesdomain-specific taskscross-domain explorationteam formationpublication-grounded conversation
Authors
Yingchaojie Feng, Zekai Shao, Yiqun Sun, Yixuan Tang, Anthony K. H. Tung
Abstract
Interdisciplinary research collaboration is crucial for scientific innovation, but it remains difficult to initiate in practice. Existing collaborator discovery approaches are often constrained by disciplinary boundaries and static researcher profiles that do not reflect the specific context of a new collaboration goal. As a result, researchers struggle to translate open-ended collaboration goals into domain-specific tasks, evaluate candidate researchers' fit and complementarity, and establish common ground before initial contact. To address these challenges, we present DeepConnect, an LLM-augmented visual analytics system for interdisciplinary collaborator discovery. DeepConnect translates collaboration ideas into domain-specific tasks, retrieves relevant papers to ground cross-domain exploration, and provides coordinated visualizations for exploring and comparing candidate researchers. It further reveals terminology gaps and overlaps across domains and supports publication-grounded conversation rehearsal to help users prepare for outreach. We evaluate DeepConnect through two case studies, a user study, and a component-level evaluation, showing its value for complementary team formation, idea refinement, and pre-contact preparation. The DeepConnect website is available at https://deepconnect.sg.