Understanding how to explain package recommendations in the clothes domain

Agung Toto Wibowo, Judith Masthoff, Advaith Siddharthan, Chenghua Lin

Research output: Contribution to conferencePaperAcademic

Abstract

Recommender system explanations have been widely studied in the context of recommending individual items to users. In this paper, we present and evaluate explanations for the more complex problem of package recommendation, where a combination of items that go well together are recommended as a package. We report the results of an empirical user study where participants try to select the most appropriate combination of a "top" (e.g. a shirt) and a "bottom" (e.g. a pair of trousers) for a hypothetical user based on one of 5 types of explanation communicating item-feature preferences and/or appropriateness of feature combinations. We found that the type of explanation significantly impacted decision time and resulted in selection of different packages, but found no difference in how participants appraised the different explanation types.

Original languageEnglish
Pages74-78
Number of pages5
Publication statusPublished - 1 Jan 2018
Event5th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems, IntRS 2018 - Vancouver, Canada
Duration: 7 Oct 2018 → …

Conference

Conference5th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems, IntRS 2018
Country/TerritoryCanada
CityVancouver
Period7/10/18 → …

Keywords

  • Clothes Domain
  • Package Explanation
  • Package Recommendation

Fingerprint

Dive into the research topics of 'Understanding how to explain package recommendations in the clothes domain'. Together they form a unique fingerprint.

Cite this