PaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Papers
arXiv:2403.02939 · doi:10.1145/3613904.3642196
Abstract
With the rapid growth of scholarly archives, researchers subscribe to "paper alert" systems that periodically provide them with recommendations of recently published papers that are similar to previously collected papers. However, researchers sometimes struggle to make sense of nuanced connections between recommended papers and their own research context, as existing systems only present paper titles and abstracts. To help researchers spot these connections, we present PaperWeaver, an enriched paper alerts system that provides contextualized text descriptions of recommended papers based on user-collected papers. PaperWeaver employs a computational method based on Large Language Models (LLMs) to infer users' research interests from their collected papers, extract context-specific aspects of papers, and compare recommended and collected papers on these aspects. Our user study (N=15) showed that participants using PaperWeaver were able to better understand the relevance of recommended papers and triage them more confidently when compared to a baseline that presented the related work sections from recommended papers.
Accepted to CHI 2024
References in corpus (7)
- Comparing Speech and Keyboard Text Entry for Short Messages in Two Languages on Touchscreen Phones
- Threddy: An Interactive System for Personalized Thread-based Exploration and Organization of Scientific Literature
- CiteSee: Augmenting Citations in Scientific Papers with Persistent and Personalized Historical Context
- Synergi: A Mixed-Initiative System for Scholarly Synthesis and Sensemaking
- From Who You Know to What You Read: Augmenting Scientific Recommendations with Implicit Social Networks
- ComLittee: Literature Discovery with Personal Elected Author Committees
- Augmenting Scientific Creativity with Retrieval across Knowledge Domains
Cited by in corpus (8)
- User Experience with LLM-powered Conversational Recommendation Systems: A Case of Music Recommendation
- PaperWave: Listening to Research Papers as Conversational Podcasts Scripted by LLM
- CorpusStudio: Surfacing Emergent Patterns in a Corpus of Prior Work while Writing
- Words as Bridges: Exploring Computational Support for Cross-Disciplinary Translation Work
- DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Exploration
- PaperBridge: Crafting Research Narratives through Human-AI Co-Exploration
- From Toil to Thought: Designing for Strategic Exploration and Responsible AI in Systematic Literature Reviews
- Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research