PaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Papers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Yoonjoo, Kang, Hyeonsu B., Latzke, Matt, Kim, Juho, Bragg, Jonathan, Chang, Joseph Chee, Siangliulue, Pao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929338114375680
author Lee, Yoonjoo
Kang, Hyeonsu B.
Latzke, Matt
Kim, Juho
Bragg, Jonathan
Chang, Joseph Chee
Siangliulue, Pao
author_facet Lee, Yoonjoo
Kang, Hyeonsu B.
Latzke, Matt
Kim, Juho
Bragg, Jonathan
Chang, Joseph Chee
Siangliulue, Pao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_02939
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Papers
Lee, Yoonjoo
Kang, Hyeonsu B.
Latzke, Matt
Kim, Juho
Bragg, Jonathan
Chang, Joseph Chee
Siangliulue, Pao
Digital Libraries
Artificial Intelligence
Computation and Language
Human-Computer Interaction
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.
title PaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Papers
topic Digital Libraries
Artificial Intelligence
Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2403.02939