DeepConnect: A Visual Analytics System for Bridging Interdisciplinary Research Collaborations

2026-08-05

AI Summary

This study addresses the challenge of initiating interdisciplinary collaboration, which is often hindered by disciplinary silos and static researcher profiles. The authors propose a novel system that integrates large language models with visual analytics to transform vague collaborative intentions into concrete domain-specific tasks. By leveraging paper retrieval to support cross-domain exploration and employing coordinated multiple views to compare candidate researchers, the system facilitates effective team formation. Its key innovation lies in synergistically combining large language models and visualization techniques to identify terminological discrepancies, align cross-disciplinary knowledge, and simulate literature-grounded pre-collaboration dialogues. Through case studies, user experiments, and component evaluations, the system demonstrates significant efficacy in enhancing team complementarity, refining collaborative ideas, and supporting preparatory communication prior to establishing research partnerships.

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.

Problem

• interdisciplinary collaboration
• collaborator discovery
• researcher profiling
• cross-domain communication
• scientific innovation

Innovation

• visual analytics
• large language models
• interdisciplinary collaboration
• collaborator discovery
• cross-domain exploration