Crowd-based personalized natural language explanations for recommendations

Shuo Chang, Max Harper, Loren G Terveen

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

61 Scopus citations

Abstract

Explanations are important for users to make decisions on whether to take recommendations. However, algorithm gen- erated explanations can be overly simplistic and unconvinc- ing. We believe that humans can overcome these limita- tions. Inspired by how people explain word-of-mouth rec- ommendations, we designed a process, combining crowd- sourcing and computation, that generates personalized nat- ural language explanations. We modeled key topical as- pects of movies, asked crowdworkers to write explanations based on quotes from online movie reviews, and personal- ized the explanations presented to users based on their rat- ing history. We evaluated the explanations by surveying 220 MovieLens users, finding that compared to personalized tag- based explanations, natural language explanations: 1) con- tain a more appropriate amount of information, 2) earn more trust from users, and 3) make users more satisfied. This paper contributes to the research literature by describing a scalable process for generating high quality and personalized natural language explanations, improving on state-of-the-art content-based explanations, and showing the feasibility and advantages of approaches that combine human wisdom with algorithmic processes.

Original languageEnglish (US)
Title of host publicationRecSys 2016 - Proceedings of the 10th ACM Conference on Recommender Systems
PublisherAssociation for Computing Machinery, Inc
Pages175-182
Number of pages8
ISBN (Electronic)9781450340359
DOIs
StatePublished - Sep 7 2016
Event10th ACM Conference on Recommender Systems, RecSys 2016 - Boston, United States
Duration: Sep 15 2016Sep 19 2016

Publication series

NameRecSys 2016 - Proceedings of the 10th ACM Conference on Recommender Systems

Other

Other10th ACM Conference on Recommender Systems, RecSys 2016
Country/TerritoryUnited States
CityBoston
Period9/15/169/19/16

Bibliographical note

Funding Information:
We thank volunteers from MovieLens community and anony-mous workers on Mturk. We also thank NSF for funding this research with grant 1017697, 964695 and 1111201.

Publisher Copyright:
© 2016 ACM.

Keywords

  • Clustering
  • Crowdsourcing
  • Natural Lan-guage Processing
  • Recommendation Explanations
  • Word2Vec

Fingerprint

Dive into the research topics of 'Crowd-based personalized natural language explanations for recommendations'. Together they form a unique fingerprint.

Cite this