PeerFinder: Finding Similar People to Guide Life Choices
Summary
PeerFinder is a visual interface that enables users to find and explore records that are similar to a seed record. PeerFinder uses both record attributes and temporal event information. To encourage engagement and inspire users’ trust in the results, PeerFinder provides different levels of controls and context that allow users to adjust the similarity criteria. It also allows users to see how similar the results are to the seed record. Intermediate results are displayed and users can iteratively refine the search.
Participants
- Fan Du, Ph.D. Candidate, Computer Science
- Catherine Plaisant, Research Scientist, UMIACS
- Ben Shneiderman, Professor, Computer Science
- Neil Spring, Associate Professor, Computer Science
Publications
- CHI’17: Fan Du, Catherine Plaisant, Neil Spring, Ben Shneiderman. Finding Similar People to Guide Life Choices: Challenge, Design, and Evaluation. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 2017 (Best Paper Honorable Mention, top 5%).
Demo Videos
Software
PeerFinder is under active development. If you have data that you would like to analyze with PeerFinder, please contact plaisant@cs.umd.edu with a description of your project. We will share the software with you in exchange for your feedback.
