PaperBridge: Crafting Research Narratives through Human-AI Co-Exploration
🤖 AI Summary
Interdisciplinary researchers (e.g., in HCI) often struggle with fragmented publication topics and weak narrative coherence. To address this, we propose a bidirectional analytical engine that integrates top-down intent-driven guidance with bottom-up thematic clustering, enabling human-AI co-construction of dynamic research narratives. The system leverages large language models for semantic content analysis and structured narrative generation, grounded in formative research and iterative interaction design. A user study (N=12) demonstrates that the tool significantly increases the diversity of explored narrative pathways and improves the clarity and contextual adaptability of scholarly contribution articulation. Our key contribution is the first application of a bidirectional evolutionary mechanism to academic narrative construction—providing a methodologically rigorous, empirically validated framework for interdisciplinary research integration and the design of scholarly communication tools.
Application Category
📝 Abstract
Researchers frequently need to synthesize their own publications into coherent narratives that demonstrate their scholarly contributions. To suit diverse communication contexts, exploring alternative ways to organize one's work while maintaining coherence is particularly challenging, especially in interdisciplinary fields like HCI where individual researchers' publications may span diverse domains and methodologies. In this paper, we present PaperBridge, a human-AI co-exploration system informed by a formative study and content analysis. PaperBridge assists researchers in exploring diverse perspectives for organizing their publications into coherent narratives. At its core is a bi-directional analysis engine powered by large language models, supporting iterative exploration through both top-down user intent (e.g., determining organization structure) and bottom-up refinement on narrative components (e.g., thematic paper groupings). Our user study (N=12) demonstrated PaperBridge's usability and effectiveness in facilitating the exploration of alternative research narratives. Our findings also provided empirical insights into how interactive systems can scaffold academic communication tasks.
Problem
Research questions and friction points this paper is trying to address.
Synthesizing diverse publications into coherent research narratives
Exploring alternative organization methods for interdisciplinary work
Balancing user intent and AI-driven narrative refinement
Innovation
Methods, ideas, or system contributions that make the work stand out.
Human-AI co-exploration system for research narratives
Bi-directional analysis engine with large language models
Supports top-down and bottom-up narrative refinement
🔎 Similar Papers
No similar papers found.
