Extracting Implicit Social Relation for Social Recommendation Techniques in User Rating Prediction

Taheri, Seyed Mohammad; Pourreza, Hamid Reza; Firouzi, Mohammad; Ghalebi, K Elahe; Grosu, Radu; Movaghar, Ali

doi:10.1145/3041021.3051153

Cited by 38 publications

(17 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We employ two popular metrics [26] root mean squared error (RMSE) and mean average error (MAE) as the evaluation methods, where MAE measures the average magnitude of the errors in a set of predictions while RMSE tends to disproportionately penalize large errors. is also means RMSE is more prone to be affected by outliers or bad predictions.…”

Section: Evaluation Protocolsmentioning

confidence: 99%

Learning to Make Document Context-Aware Recommendation with Joint Convolutional Matrix Factorization

Guo

Jiang

et al. 2020

Complexity

View full text Add to dashboard Cite

Context-aware recommendation (CR) is the task of recommending relevant items by exploring the context information in online systems to alleviate the data sparsity issue of the user-item data. Prior methods mainly studied CR by document-based modeling approaches, that is, making recommendations by additionally utilizing textual data such as reviews, abstracts, or synopses. However, due to the inherent limitation of the bag-of-words model, they cannot effectively utilize contextual information of the documents, which results in a shallow understanding of the documents. Recent works argued that the understanding of document context can be improved by the convolutional neural network (CNN) and proposed the convolutional matrix factorization (ConvMF) to leverage the contextual information of documents to enhance the rating prediction accuracy. However, ConvMF only models the document content context from an item view and assumes users are independent and identically distributed (i.i.d). But in reality, as we often turn to our friends for recommendations, the social relationship and social reviews are two important factors that can change our mind most. Moreover, users are more inclined to interact (buy or click) with the items that they have bought (or clicked). The relationships among items are also important factors that can impact the user’s final decision. Based on the above observations, in this work, we target CR and propose a joint convolutional matrix factorization (JCMF) method to tackle the encountered challenges, which jointly considers the item’s reviews, item’s relationships, user’s social influence, and user’s reviews in a unified framework. More specifically, to explore items’ relationships, we introduce a predefined item relation network into ConvMF by a shared item latent factor and propose a method called convolutional matrix factorization with item relations (CMF-I). To consider user’s social influence, we further integrate the user’s social network into CMF-I by sharing the user latent factor between user’s social network and user-item rating matrix, which can be treated as a regularization term to constrain the recommendation process. Finally, to model the document contextual information of user’s reviews, we exploit another CNN to learn user’s content representations and achieve our final model JCMF. We conduct extensive experiments on the real-world dataset from Yelp. The experimental results demonstrate the superiority of JCMF compared to several state-of-the-art methods in terms of root mean squared error (RMSE) and mean average error (MAE).

show abstract

Section: Evaluation Protocolsmentioning

confidence: 99%

Learning to Make Document Context-Aware Recommendation with Joint Convolutional Matrix Factorization

Guo

Jiang

et al. 2020

Complexity

View full text Add to dashboard Cite

show abstract

“…ls and λ are two constants, where ls is the learning step and λ is the regularization parameter. To minimize the prediction error, the optimal experimental settings is ls = 0.01 and λ = 0.1 [28].…”

Section: Regsvdmentioning

confidence: 99%

Like-tasted user groups to predict ratings in recommender systems

Jaffali

Jamoussi

Smaïli

et al. 2020

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

Recommendation Systems have gained the intention of many researchers due to the growth of the business of personalizing, sorting and suggesting products to customers. Most of rating prediction in recommendation systems are based on customer preferences or on the historical behavior of similar customers. The similarity between customers is generally measured by the number of times customers liked or disliked the same item. Given the huge number and the variety of items, many customers cannot be considered as similar, as they did not evaluate the same items, even if they have similar tastes. This paper presents a new method of rating prediction in recommendation systems. The proposed method starts by identifying the taste directions or the interest centers based on the users' demographic information combined with their previous evaluations. Thus, it uses the Principal Component Analysis (PCA) to retrieve the major taste orientations. According to these orientations, user groups are created. Then, for each group, it generates a prediction model, that will be used to predict unknown rates of users within the corresponding group. In order to assess the accuracy of the proposed method, we compare its

show abstract

“…Recently, RSs are no longer depending on the rating matrix only for the purpose of producing an accurate personalized recommendation, but they try to make use of various kind of available data on the web. This include the users" demography [1], [2] users and items features [3], [4], tags and time [5], social relation [6], [7] contextual features [8]- [10], and geographic information [11], [12] which are somehow incorporated into the recommendation models for the purpose of improving the performance of the recommendation.…”

Section: Introductionmentioning

confidence: 99%

Tensorized Neural Network for Multi-Aspect Rating-Based Recommendation

2019

IJRTE

View full text Add to dashboard Cite

Generating personalized recommendations is one of the most crucial aspects in Recommender System research area. Most of the researches only focus on the accuracy of recommendation using collaborative filtering that relies on a single overall rating that represents the overall preferences. However, the user may have a different emphasis on different specific aspects that affect the users’ final rating decisions. Therefore, we present a neural network model that utilize multi-aspects ratings using Tensor Factorization to improve the accuracy of personalization, as well as optimizing the dynamic weights of the aspect. To measure the estimated weights for the aspects, we employ the Higher Order Singular Value Decomposition (HOSVD) technique called CANDECOMP/PARAFAC (CP) decomposition that allows for multi-faceted data processing. We then develop the Neural Network with backpropagation error to train the model with different parameter settings and limited computational time. We also use a non-linear activation function in each hidden layer in various settings. The experimental result measured using MAE shows that the proposed model has significantly outperformed the baseline approach in terms of the prediction accuracy. Based on the observation, the performance of rating prediction has been improved by employing the Tensorized Neural Network model and can overcome the problem of local optimum convergence for multi-aspect rating recommendation.

show abstract

Extracting Implicit Social Relation for Social Recommendation Techniques in User Rating Prediction

Cited by 38 publications

References 45 publications

Learning to Make Document Context-Aware Recommendation with Joint Convolutional Matrix Factorization

Learning to Make Document Context-Aware Recommendation with Joint Convolutional Matrix Factorization

Like-tasted user groups to predict ratings in recommender systems

Tensorized Neural Network for Multi-Aspect Rating-Based Recommendation

Contact Info

Product

Resources

About