Abstract
Bayesian Personalized Ranking (BPR) is a well-known recommendation framework that learns to rank items based on one-class implicit feedback. In some domains such as video and music streaming and news aggregator websites, users’ implicit feedback is not limited to one-class feedback as there are other types of feedback such as watching, listening and reading time which are continuous. This feedback reflects the consumption behavior of users. In this research we show that using this kind of implicit feedback on the top of one-class feedback, recommender systems are able to learn user preferences more precisely. We propose an extended form of BPR by including user consumption behavior to recommend news topics. The result shows that using the extended form of BPR with consumption information improves the performance based on four evaluation measures. The result also verifies that by considering a more granular feedback the extended BPR has better predictions.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
