HRS-CE: A hybrid framework to integrate content embeddings in recommender systems for cold start items

Abstract Recommender systems (RSs) provide the personalized recommendations to users for specific items in a wide range of applications such as e-commerce, media recommendations and social networking applications. Collaborative Filtering (CF) and Content Based (CB) Filtering are two methods which have been employed in implementing the recommender systems. CF suffers from Cold Start (CS) problem where no rating records (Complete Cold Start CSS) or very few records (Incomplete Cold Start ICS) are available for newly coming users and items. The performance of CB methods relies on good feature extraction methods so that the item descriptions can be used to measure items similarity as well as for user profiling. This paper addresses the CS problem by providing a novel way of integrating content embeddings in CF. The proposed algorithm (HRS-CE) generates the user profiles that depict the type of content in which a particular user is interested. The word embedding model (Word2Vec) is used to produce distributed representation of items descriptions. The higher representation for an item description, obtained using content embeddings, are combined with similarity techniques to perform rating predictions. The proposed method is evaluated on two public benchmark datasets (MovieLens 100k and MovieLens 20M). The results demonstrate that the proposed model outperforms the state of the art recommender system models for CS items.

[1]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[2]  Jun Wang,et al.  Unifying user-based and item-based collaborative filtering approaches by similarity fusion , 2006, SIGIR.

[3]  John Riedl,et al.  Item-based collaborative filtering recommendation algorithms , 2001, WWW '01.

[4]  Yehuda Koren,et al.  Matrix Factorization Techniques for Recommender Systems , 2009, Computer.

[5]  Haoran Xie,et al.  Folksonomy-based personalized search by hybrid user profiles in multiple levels , 2016, Neurocomputing.

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

[7]  Yehuda Koren,et al.  Factorization meets the neighborhood: a multifaceted collaborative filtering model , 2008, KDD.

[8]  Padhraic Smyth,et al.  KDD Cup and Workshop 2007 , 2007, KDD '07.

[9]  Pasquale Lops,et al.  Content-based Recommender Systems: State of the Art and Trends , 2011, Recommender Systems Handbook.

[10]  Michael R. Lyu,et al.  Learning to recommend with explicit and implicit social relations , 2011, TIST.

[11]  Dennis M. Wilkinson,et al.  Large-Scale Parallel Collaborative Filtering for the Netflix Prize , 2008, AAIM.

[12]  Shuang-Hong Yang,et al.  Functional matrix factorizations for cold-start recommendation , 2011, SIGIR.

[13]  Daniel Thalmann,et al.  Merging trust in collaborative filtering to alleviate data sparsity and cold start , 2014, Knowl. Based Syst..

[14]  Iván Cantador,et al.  Time-aware recommender systems: a comprehensive survey and analysis of existing evaluation protocols , 2013, User Modeling and User-Adapted Interaction.

[15]  Yoav Shoham,et al.  Fab: content-based, collaborative recommendation , 1997, CACM.

[16]  Jie Zhang,et al.  TopicMF: Simultaneously Exploiting Ratings and Reviews for Recommendation , 2014, AAAI.

[17]  Kai Chen,et al.  Collaborative filtering and deep learning based recommendation system for cold start items , 2017, Expert Syst. Appl..

[18]  Angshul Majumdar,et al.  A Comprehensive Recommender System Model: Improving Accuracy for Both Warm and Cold Start Users , 2015, IEEE Access.

[19]  Lior Rokach,et al.  Introduction to Recommender Systems Handbook , 2011, Recommender Systems Handbook.

[20]  Guisheng Yin,et al.  Collaborative Filtering Recommendation on Users’ Interest Sequences , 2016, PloS one.

[21]  Kai Chen,et al.  Joint Prediction of Rating and Popularity for Cold-Start Item by Sentinel User Selection , 2016, IEEE Access.

[22]  Ruslan Salakhutdinov,et al.  Probabilistic Matrix Factorization , 2007, NIPS.

[23]  Haoran Xie,et al.  Discover learning path for group users: A profile-based approach , 2017, Neurocomputing.

[24]  Benjamin M. Marlin,et al.  Modeling User Rating Profiles For Collaborative Filtering , 2003, NIPS.

[25]  Taghi M. Khoshgoftaar,et al.  A Survey of Collaborative Filtering Techniques , 2009, Adv. Artif. Intell..

[26]  Yehuda Koren,et al.  Advances in Collaborative Filtering , 2011, Recommender Systems Handbook.

[27]  Gediminas Adomavicius,et al.  Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.

[28]  Naixue Xiong,et al.  Cold-Start Recommendation Using Bi-Clustering and Fusion for Large-Scale Social Recommender Systems , 2014, IEEE Transactions on Emerging Topics in Computing.

[29]  F. Maxwell Harper,et al.  The MovieLens Datasets: History and Context , 2016, TIIS.

[30]  Ruslan Salakhutdinov,et al.  Bayesian probabilistic matrix factorization using Markov chain Monte Carlo , 2008, ICML '08.

[31]  Liu Yu,et al.  A feature-based regression algorithm for cold-start recommendation , 2014 .

[32]  Arindam Banerjee,et al.  Generalized Probabilistic Matrix Factorizations for Collaborative Filtering , 2010, 2010 IEEE International Conference on Data Mining.

[33]  Neil Yorke-Smith,et al.  TrustSVD: Collaborative Filtering with Both the Explicit and Implicit Influence of User Trust and of Item Ratings , 2015, AAAI.

[34]  Hanghang Tong,et al.  Ice-Breaking: Mitigating Cold-Start Recommendation Problem by Rating Comparison , 2015, IJCAI.

[35]  Roliana Ibrahim,et al.  Cross Domain Recommender Systems , 2017, ACM Comput. Surv..

[36]  Tao Zhou,et al.  Solving the cold-start problem in recommender systems with social tags , 2010 .