Relational Collaborative Topic Regression for Recommender Systems

Abstract

Abstract-Due to its successful application in recommender systems, collaborative filtering (CF) has become a hot research topic in data mining and information retrieval. In traditional CF methods, only the feedback matrix, which contains either explicit feedback (also called ratings) or implicit feedback on the items given by users, is used for training and prediction. Typically, the feedback matrix is sparse, which means that most users interact with few items. Due to this sparsity problem, traditional CF with only feedback information will suffer from unsatisfactory performance. Recently, many researchers have proposed to utilize auxiliary information, such as item content (attributes), to alleviate the data sparsity problem in CF. Collaborative topic regression (CTR) is one of these methods which has achieved promising performance by successfully integrating both feedback information and item content information. In many real applications, besides the feedback and item content information, there may exist relations (also known as networks) among the items which can be helpful for recommendation. In this paper, we develop a novel hierarchical Bayesian model called Relational Collaborative Topic Regression (RCTR), which extends CTR by seamlessly integrating the user-item feedback information, item content information, and network structure among items into the same model. Experiments on real-world datasets show that our model can achieve better prediction accuracy than the state-of-the-art methods with lower empirical training time. Moreover, RCTR can learn good interpretable latent structures which are useful for recommendation.

A novel collective matrix factorization model for recommendation with fine‐grained social trust prediction

“…Generally speaking, traditional recommender systems can be divided into two categories. The first class is content‐based filtering (CBF) which has been mainly employed in textual fields like recommendations of news or scholarly paper . CBF is very useful for extracting topics from item content and user profiles.…”

“…The low dimensional matrices are multiplied directly to make further rating predictions. Extensive works based on matrix factorization framework have been proposed to incorporate auxiliary information like social relation, item meta data, and temporal information …”

“…The first class is content-based filtering (CBF) which has been mainly employed in textual fields like recommendations of news or scholarly paper. 23,24 CBF is very useful for extracting topics from item content and user profiles. The second category is collaborative filtering (CF); this technique is undoubtedly better than CBF when we need to recommend users with video or images where their content are difficult to be extracted, especially before the widely application of deep learning techniques.…”

Collaborative recommendation with user generated content

“…Recently, there are a few works that built statistical models to utilize item descriptions in recommender systems (Agarwal and Chen, 2010;Wang and Blei, 2011;Purushotham etal., 2012;Chen et al, 2014a;Wang and Li, 2014;Zhang and Wang, 2014). Wang and Blei (2011) proposed a hybrid prediction model named collaborative topic regression (denoted by CTR), which combined latent Dirichlet allocation (LDA) and matrix factorization (MF) together.…”

Personalized Opinion-Based Recommendation

“…And the type of rating data used by collaborative filtering approaches can be notoriously sparse. This has led researchers to develop hybrid models that make the best of both worlds [8] and also led to the exploit of auxiliary information; see [9,10].…”