Latent Factor Representations for Cold-Start Video Recommendation

Recommending items that have rarely/never been viewed by users is a bottleneck for collaborative filtering (CF) based recommendation algorithms. To alleviate this problem, item content representation (mostly in textual form) has been used as auxiliary information for learning latent factor representations. In this work we present a novel method for learning latent factor representation for videos based on modelling the emotional connection between user and item. First of all we present a comparative analysis of state-of-the art emotion modelling approaches that brings out a surprising finding regarding the efficacy of latent factor representations in modelling emotion in video content. Based on this finding we present a method visual-CLiMF for learning latent factor representations for cold start videos based on implicit feedback. Visual-CLiMF is based on the popular collaborative less-is-more approach but demonstrates how emotional aspects of items could be used as auxiliary information to improve MRR performance. Experiments on a new data set and the Amazon products data set demonstrate the effectiveness of visual-CLiMF which outperforms existing CF methods with or without content information.

[1]  Chong Wang,et al.  Collaborative topic modeling for recommending scientific articles , 2011, KDD.

[2]  Sheng Wang,et al.  SUIT: A Supervised User-Item Based Topic Model for Sentiment Analysis , 2014, AAAI.

[3]  K. Scherer.  What are emotions? And how can they be measured? , 2005 .

[4]  Erik Cambria,et al.  AffectiveSpace 2: Enabling Affective Intuition for Concept-Level Sentiment Analysis , 2015, AAAI.

[5]  Julian J. McAuley,et al.  VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback , 2015, AAAI.

[6]  Mara Mather,et al.  Beyond arousal and valence: The importance of the biological versus social relevance of emotional stimuli , 2012, Cognitive, affective & behavioral neuroscience.

[7]  Zornitsa Kozareva,et al.  Sentiment Prediction Using Collaborative Filtering , 2013, ICWSM.

[8]  Bernd Ludwig,et al.  Matrix factorization techniques for context aware recommendation , 2011, RecSys '11.

[9]  Allan Hanbury,et al.  Affective image classification using features inspired by psychology and art theory , 2010, ACM Multimedia.

[10]  J. Stainer,et al.  The Emotions , 1922, Nature.

[11]  Bolei Zhou,et al.  Learning Deep Features for Scene Recognition using Places Database , 2014, NIPS.

[12]  Dit-Yan Yeung,et al.  Collaborative Deep Learning for Recommender Systems , 2014, KDD.

[13]  Xiangyang Xue,et al.  Predicting Emotions in User-Generated Videos , 2014, AAAI.

[14]  Jure Leskovec,et al.  Inferring Networks of Substitutable and Complementary Products , 2015, KDD.

[15]  Martha Larson,et al.  Collaborative Filtering beyond the User-Item Matrix , 2014, ACM Comput. Surv..

[16]  Weisi Lin,et al.  Personality, Culture, and System Factors - Impact on Affective Response to Multimedia , 2016, ArXiv.

[17]  Tsuhan Chen,et al.  A mixed bag of emotions: Model, predict, and transfer emotion distributions , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Martha Larson,et al.  CLiMF: learning to maximize reciprocal rank with collaborative less-is-more filtering , 2012, RecSys.

[19]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[20]  Thierry Pun,et al.  Multimodal Emotion Recognition in Response to Videos , 2012, IEEE Transactions on Affective Computing.

[21]  Mu Zhu,et al.  Content-boosted matrix factorization for recommender systems: experiments with recipe recommendation , 2011, RecSys '11.

[22]  Rongrong Ji,et al.  SentiBank: large-scale ontology and classifiers for detecting sentiment and emotions in visual content , 2013, ACM Multimedia.

[23]  Qiang Ji,et al.  Video Affective Content Analysis: A Survey of State-of-the-Art Methods , 2015, IEEE Transactions on Affective Computing.

[24]  Yifan Hu,et al.  Collaborative Filtering for Implicit Feedback Datasets , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[25]  Lars Schmidt-Thieme,et al.  BPR: Bayesian Personalized Ranking from Implicit Feedback , 2009, UAI.

[26]  Mohammad Soleymani,et al.  Corpus Development for Affective Video Indexing , 2012, IEEE Transactions on Multimedia.

[27]  Daniela Braga,et al.  It’s Not Just What You Say, But How You Say It: Muiltimodal Sentiment Analysis Via Crowdsourcing , 2016, Proceedings of the AAAI Conference on Human Computation and Crowdsourcing.

[28]  Royi Ronen,et al.  Selecting content-based features for collaborative filtering recommenders , 2013, RecSys.