VitaLITy logo

Promoting Serendipitous Discovery of Academic Literature with Transformers & Visual Analytics

Arpit Narechania, Alireza Karduni, Ryan Wesslen, Emily Wall
Georgia Tech, UNC Charlotte, Northwestern University, Emory University

Welcome to VitaLITy

There are a few prominent practices for conducting reviews of academic literature, including searching for specific keywords on Google Scholar or checking citations from some initial seed paper(s). These approaches serve a critical purpose for academic literature reviews, yet there remain challenges in identifying relevant literature when similar work may utilize different terminology (e.g., mixed-initiative visual analytics papers may not use the same terminology as papers on model-steering, yet the two topics are relevant to one another).

We introduce a system, VitaLITy, intended to complement existing practices. In particular, VitaLITy promotes serendipitous discovery of relevant literature using transformer language models, allowing users to find semantically similar papers in a word embedding space given (1) a list of input paper(s) or (2) a working abstract. VitaLITy visualizes this document-level embedding space in an interactive 2-D scatterplot using dimension reduction. VitaLITy also summarizes meta information about the document corpus or search query, including keywords and co-authors, and allows users to save and export papers for use in a literature review. We present qualitative findings from an evaluation of VitaLITy, suggesting it can be a promising complementary technique for conducting academic literature reviews. Furthermore, we contribute data from 38 popular data visualization publication venues in VitaLITy, and we provide scrapers for the open-source community to continue to grow the list of supported venues.


VitaLITy Overview

Getting started is easy!


Dataset of Academic Articles

Explore our dataset of 59,232 academic articles with metadata (e.g., Authors, Titles, Keywords) and document embeddings (e.g., Specter).

Academic Articles Web Scraper

Leverage and contribute to our Python scraper that scrapes metadata from digital libraries (e.g., ACM Digital Library)

RESTful API for Similarity Search

Utilize our RESTful API to query for similar papers by a list of seed papers or a working abstract.

Interactive Visualization

Explore the document corpus of academic articles in our scalable, interactive UI.