Movie Rating Prediction using Multimedia Content and Modeling as a Classification Problem

Published in MediaEval 2018 Multimedia Benchmark Workshop, 2018

Recommended citation: Fatemeh Nazary, Yashar Deldjoo Working Notes Proceedings of the MediaEval 2018 Workshop (MediaEval 2018).

[DOI] [PDF] [bibtex]


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 func- tions. Results are promising and show the potentials for leveraging the audiovisual content for improving the quality of exiting movie recommendation systems in service.