This paper presents the method proposed for the recommender system task in Mediaeval 2018 on predicting user global ratings given to movies and their standard deviation through the audiovisual content and the associated metadata. In the proposed work, we model the rating prediction problem as a classification problem and employ different classifiers for the prediction task. Furthermore, in order to obtain a video-level representation of features from clip-level features, we employ statistical summarization functions. Results are promising and show the potential of leveraging the audiovisual content for improving the quality of existing movie recommendation systems in service. Copyright held by the owner/author(s).

Movie rating prediction using multimedia content and modeling as a classification problem

Fatemeh Nazary;Yashar Deldjoo
2018-01-01

Abstract

This paper presents the method proposed for the recommender system task in Mediaeval 2018 on predicting user global ratings given to movies and their standard deviation through the audiovisual content and the associated metadata. In the proposed work, we model the rating prediction problem as a classification problem and employ different classifiers for the prediction task. Furthermore, in order to obtain a video-level representation of features from clip-level features, we employ statistical summarization functions. Results are promising and show the potential of leveraging the audiovisual content for improving the quality of existing movie recommendation systems in service. Copyright held by the owner/author(s).
2018
Working Notes Proceedings of the MediaEval Workshop, MediaEval 2018
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11589/196527
Citazioni
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact