Exploring the Role of Local and Global Explanations in Recommender Systems

Marissa Radensky, Doug Downey, Kyle Lo, Zoran Popovic, Daniel S. Weld

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Explanations are well-known to improve recommender systems' transparency. These explanations may be local, explaining individual recommendations, or global, explaining the recommender model overall. Despite their widespread use, there has been little investigation into the relative benefits of the two explanation approaches. We conducted a 30-participant exploratory study and a 30-participant controlled user study with a research-paper recommender to analyze how providing local, global, or both explanations influences user understanding of system behavior. Our results provide evidence suggesting that both are more helpful than either alone for explaining how to improve recommendations, yet both appeared less helpful than global alone for efficiently identifying false positive and negative recommendations. However, we note that the two explanation approaches may be better compared in a higher-stakes or more opaque domain.

Original languageEnglish (US)
Title of host publicationCHI 2022 - Extended Abstracts of the 2022 CHI Conference on Human Factors in Computing Systems
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450391566
DOIs
StatePublished - Apr 27 2022
Event2022 CHI Conference on Human Factors in Computing Systems, CHI EA 2022 - Virtual, Online, United States
Duration: Apr 30 2022May 5 2022

Publication series

NameConference on Human Factors in Computing Systems - Proceedings

Conference

Conference2022 CHI Conference on Human Factors in Computing Systems, CHI EA 2022
Country/TerritoryUnited States
CityVirtual, Online
Period4/30/225/5/22

Keywords

  • explainable AI
  • human-AI interaction

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design
  • Software

Fingerprint

Dive into the research topics of 'Exploring the Role of Local and Global Explanations in Recommender Systems'. Together they form a unique fingerprint.

Cite this