Sharing geotagged pictures for an Emotion-based Recommender System

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

Recommender systems are prominently used for movie or app recommendation or in e-commerce by considering profiles, past preferences and increasingly also further personalized measures. We designed and implemented an emotion-based recommender system for city visitors that takes into account user emotion and user location for the recommendation process. We conducted a comparative study between the emotion-based recommender system and recommender systems based on traditional measures. Our evaluation study involved 28 participators and the experiments showed that the emotion-based recommender system increased the average rating of the recommendation by almost 19%. We conclude that the use of emotion can significantly improve the results and especially their level of personalization.

Original languageEnglish
Title of host publication2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2021
PublisherIEEE
Pages68-73
Number of pages6
ISBN (Electronic)9781665404242
DOIs
Publication statusPublished - 25 May 2021
MoE publication typeA4 Article in a conference publication
EventIEEE International Conference on Pervasive Computing and Communications Workshops - Kassel, Germany
Duration: 22 Mar 202126 Mar 2021
https://www.percom.org/

Publication series

Name2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2021

Conference

ConferenceIEEE International Conference on Pervasive Computing and Communications Workshops
Abbreviated titlePerCom Workshops
Country/TerritoryGermany
CityKassel
Period22/03/202126/03/2021
Internet address

Keywords

  • Artificial Intelligence
  • City tour guide
  • Emotions
  • Recommender Systems

Fingerprint

Dive into the research topics of 'Sharing geotagged pictures for an Emotion-based Recommender System'. Together they form a unique fingerprint.

Cite this