SciSight: Combining faceted navigation and research group detection for COVID-19 exploratory scientific search

Abstract

The COVID-19 pandemic has sparked unprecedented mobilization of scientists, already generating thousands of new papers that join a litany of previous biomedical work in related areas. This deluge of information makes it hard for researchers to keep track of their own field, let alone explore new directions. Standard search engines are designed primarily for targeted search and are not geared for discovery or making connections that are not obvious from reading individual papers.In this paper, we present our ongoing work on SciSight, a novel framework for exploratory search of COVID-19 research. Based on formative interviews with scientists and a review of existing tools, we build and integrate two key capabilities: first, exploring interactions between biomedical facets (e.g., proteins, genes, drugs, diseases, patient characteristics); and second, discovering groups of researchers and how they are connected. We extract entities using a language model pre-trained on several biomedical information extraction tasks, and enrich them with data from the Microsoft Academic Graph (MAG). To find research groups automatically, we use hierarchical clustering with overlap to allow authors, as they do, to belong to multiple groups. Finally, we introduce a novel presentation of these groups based on both topical and social affinities, allowing users to drill down from groups to papers to associations between entities, and update query suggestions on the fly with the goal of facilitating exploratory navigation.SciSight 1 has thus far served over 10K users with over 30K page views and 13% returning users. Preliminary user interviews with biomedical researchers suggest that SciSight complements current approaches and helps find new and relevant knowledge. * Denotes equal contribution 1

Deep Learning applications for COVID-19

“…In SciSight [64], the authors design a knowledge graph that is integrated with the social dynamics of scientific research. They motivate their approach highlighting that most of these Literature Mining systems are designed for targeted search.…”

Accelerating COVID-19 research with graph mining and transformer-based learning

“…The vastness of COVID-19 literature also spurned the need for having systems that could allow researchers and base users alike to get their COVID-19 queries answered. Systems like CKG (Wise et al) [41] and SciSight (Hope et al) [14] currently provide this functionality. While we do aim to provide an easy to use webframework for medical researchers, the scope of the aforementioned systems is beyond the scope of our work.…”

“…[41] and SciSight (Hope et al .) [14] currently provide this functionality. While we do aim to provide an easy to use web-framework for medical researchers, the scope of the aforementioned systems is beyond the scope of our work.…”

Text mining approaches for dealing with the rapidly expanding literature on COVID-19

“…Visualizations are usually coupled with extracted KBs or citation networks and provide an alternate way to explore a corpus of scientific papers. Examples include SemViz [ 92 ] ( Row S36 ), which focuses on exploration of the CORD-19 corpus, the Blender Lab COVID-KG and protein–protein interaction datasets and SciSight [ 33 ] ( Row S38 ), which allows users to browse the documents in CORD-19 by author, institutional affiliation, extracted entities and network relationships.…”