Self-Attentive Recommendation for Multi-Source Review Package

With the diversified sources satisfying users' needs, many online service platforms collect information from multiple sources in order to provide a set of useful information to the users. However, existing recommendation systems are mostly designed for single-source data, and thus fail to recommend multi-source review packages since the interplay between the reviews of different sources is not properly modeled. In fact, modeling the interplay between different sources is challenging because 1) two reviews may conflict with each other, 2) different users have different preferences on review sources, and 3) users' preferences to each source may change under different scenarios. To address these challenges, we propose Self-Attentive Recommendation for multi-source review Package (SARP), for predicting how useful the user feels to the package, while simultaneously reflecting how much the user is affected by each review. Specifically, SARP jointly considers the relationships of every user, purpose, and review source to learn better latent representations. A self-attention module is further used for integrating source representations and the review ratings, following a multi-layer perceptron (MLP) for the prediction tasks. Experimental results on the self-constructed dataset and public dataset demonstrate that the proposed model outperforms the state-of-the-art approaches.

[1]  Junjun Li,et al.  Bundle recommendation in ecommerce , 2014, SIGIR.

[2]  Jang-Sun Hwang,et al.  How Consumers Evaluate eWOM (Electronic Word-of-Mouth) Messages , 2009, Cyberpsychology Behav. Soc. Netw..

[3]  Tat-Seng Chua,et al.  Neural Factorization Machines for Sparse Predictive Analytics , 2017, SIGIR.

[4]  Yongfeng Zhang,et al.  Sequential Recommendation with User Memory Networks , 2018, WSDM.

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

[6]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[7]  Nadia Magnenat-Thalmann,et al.  Time-aware point-of-interest recommendation , 2013, SIGIR.

[8]  Xing Xie,et al.  xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems , 2018, KDD.

[9]  Martin Ester,et al.  Collaborative Denoising Auto-Encoders for Top-N Recommender Systems , 2016, WSDM.

[10]  Juan Luis Nicolau,et al.  Asymmetric effects of online consumer reviews , 2015 .

[11]  Zibin Zheng,et al.  Matching User with Item Set: Collaborative Bundle Recommendation with Deep Attention Network , 2019, IJCAI.

[12]  Lina Yao,et al.  Context-aware Point-of-Interest Recommendation Using Tensor Factorization with Social Regularization , 2015, SIGIR.

[13]  Guorui Zhou,et al.  Deep Interest Network for Click-Through Rate Prediction , 2017, KDD.

[14]  Qian Zhang,et al.  Cross-Domain Recommendation with Multiple Sources , 2020, 2020 International Joint Conference on Neural Networks (IJCNN).

[15]  Junlin Zhang,et al.  FiBiNET: combining feature importance and bilinear feature interaction for click-through rate prediction , 2019, RecSys.

[16]  Yunming Ye,et al.  DeepFM: A Factorization-Machine based Neural Network for CTR Prediction , 2017, IJCAI.

[17]  Steffen Rendle,et al.  Factorization Machines , 2010, 2010 IEEE International Conference on Data Mining.

[18]  Heng-Tze Cheng,et al.  Wide & Deep Learning for Recommender Systems , 2016, DLRS@RecSys.

[19]  Hui Xiong,et al.  A Cocktail Approach for Travel Package Recommendation , 2014, IEEE Transactions on Knowledge and Data Engineering.

[20]  Xing Xie,et al.  Collaborative Metric Learning with Memory Network for Multi-Relational Recommender Systems , 2019, IJCAI.

[21]  Scott Sanner,et al.  AutoRec: Autoencoders Meet Collaborative Filtering , 2015, WWW.

[22]  Tat-Seng Chua,et al.  Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks , 2017, IJCAI.

[23]  Wen-Chih Peng,et al.  Sequence-Aware Factorization Machines for Temporal Predictive Analytics , 2019, 2020 IEEE 36th International Conference on Data Engineering (ICDE).

[24]  Ulrich Paquet,et al.  Beyond Collaborative Filtering: The List Recommendation Problem , 2016, WWW.

[25]  J. Chang,et al.  Analysis of individual differences in multidimensional scaling via an n-way generalization of “Eckart-Young” decomposition , 1970 .

[26]  Xing Xie,et al.  Neural News Recommendation with Attentive Multi-View Learning , 2019, IJCAI.

[27]  Julian J. McAuley,et al.  Generating and Personalizing Bundle Recommendations on Steam , 2017, SIGIR.

[28]  Chang Zhou,et al.  Deep Interest Evolution Network for Click-Through Rate Prediction , 2018, AAAI.

[29]  Huaping Chen,et al.  Credibility of Electronic Word-of-Mouth: Informational and Normative Determinants of On-line Consumer Recommendations , 2009, Int. J. Electron. Commer..

[30]  Keping Yang,et al.  Deep Session Interest Network for Click-Through Rate Prediction , 2019, IJCAI.

[31]  Xiangning Chen,et al.  DeepAPF: Deep Attentive Probabilistic Factorization for Multi-site Video Recommendation , 2019, IJCAI.

[32]  M. Birnbaum,et al.  Source Credibility in Social Judgment : Bias , Expertise , and the Judge ' s Point of View , 1979 .