Donkers, Tim; Loepp, Benedikt; Ziegler, Jürgen:
Towards Understanding Latent Factors and User Profiles by Enhancing Matrix Factorization with Tags
In: Poster-RecSys 2016 : Poster Proceedings of ACM RecSys 2016 / Guy, Ido; Sharma, Amit (Hrsg.). - 10th ACM Conference on Recommender Systems (RecSys 2016), 17. September 2016, Boston, USA - 2016 - (CEUR workshop proceedings ; 1688)
2016Poster in TagungsbandOA Gold
InformatikFakultät für Ingenieurwissenschaften » Informatik und Angewandte Kognitionswissenschaft » Informatik » Interaktive Systeme / Interaktionsdesign
Titel in Englisch:
Towards Understanding Latent Factors and User Profiles by Enhancing Matrix Factorization with Tags
Autor(in):
Donkers, TimLSF; Loepp, BenediktLSF; Ziegler, JürgenLSF
WWW URL
Sprache des Textes
Englisch
Schlagwort, Thema:
Recommender Systems ; Interactive Recommending ; Matrix Factorization ; Tags ; User Profiles ; Explanations

Abstract in Englisch:

With the interactive recommending approach we have re- cently proposed, users are given more control over model- based Collaborative Filtering while the results are perceived as more transparent. Integrating the latent factors derived by Matrix Factorization with tags users provided for the items has, however, even more advantages. In this paper, we show how general understanding of the abstract factor space, and of user and item positions inside it, can benet from the semantics introduced by considering additional in- formation. Moreover, our approach allows us to explain the user's (former latent) preference prole by means of tags.