Relatedly: Scaffolding Literature Reviews with Existing Related Work Sections

Abstract

Scholars who want to research a scientific topic must take time to read, extract meaning, and identify connections across many papers. As scientific literature grows, this becomes increasingly challenging. Meanwhile, authors summarize prior research in papers' related work sections, though this is scoped to support a single paper. A formative study found that while reading multiple related work paragraphs helps overview a topic, it is hard to navigate overlapping and diverging references and research foci. In this work, we design a system, Relatedly, that scaffolds exploring and reading multiple related work paragraphs on a topic, with features including dynamic re-ranking and highlighting to spotlight unexplored dissimilar information, auto-generated descriptive paragraph headings, and low-lighting of redundant information. From a within-subjects user study (n=15), we found that scholars generate more coherent, insightful, and comprehensive topic outlines using Relatedly compared to a baseline paper list. CCS CONCEPTS• Human-centered computing → Graphical user interfaces.

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

“…There is a recent thread of research focusing on how to reuse content from the related work sections of published papers to help scholars deeply understand the literature. For example, Relatedly [43] allowed its users to search across related work sections extracted from many published papers and provided support for reading scattered paragraphs. It highlighted how rich synthesis contained in related work sections can help scholars better understand the landscape of a research field while gaining a deep understanding of how different prior work compare and contrast with one another.…”

“…Future work could explore ways to allow users to further customize their paper alerts by adjusting the complexity of the descriptions. One opportunity for future work in this direction is to look to research that focuses on automatic related work section generation [43] or multi-document summarization [21] that aimed to generate descriptions for many documents. One interesting and relevant use case we observed in the user study was one participant who had saved a survey paper in their folder.…”