Learning product representations for generating reviews for cold products

Existing work in the literature have shown that the number and quality of product ratings and reviews have a direct correlation with the product purchase rates in online e-commerce portals. However, the majority of the products on e-commerce portals do not have any ratings or reviews and are known as cold products (⇠90% of products on Amazon are cold). As such, there has been growing interest in generating reviews for cold products by selectively transferring reviews from other similar yet warm products. Our work in this paper focuses on this specific problem and generates reviews for cold products through review selection. Similar to existing work in the literature, our work assumes a relationship between product attribute-values and the reviews that products receive. However, unlike the literature, our method (1) is not restricted to the exact surface form of a product attribute name; and, (2) can distinguish between the same attribute expressed in different forms. We achieve these two important characteristics by proposing methods to learn neural product representations that capture the semantics of product attribute-values as they relate to user reviews. More specifically, our work o↵ers (i) an approach to learn neural representations of product attribute-values within a shared embedding space as product reviews; (ii) a weighted composition strategy to develop product representations from the representation of its attributes; and, (iii) a review selection method that selects relevant reviews for the composed product representation within the neural embedding space. We show through our extensive experiments on five datasets consisting of products from CNET.com and movies from rottentomatoes.com that our method is able to show stronger performance compared to several baselines on ROUGE-2 metrics. Preprint submitted to Elsevier April 1, 2021 Man scrip Click here to ie linked References

[1]  Nicholas Jing Yuan,et al.  Collaborative Knowledge Base Embedding for Recommender Systems , 2016, KDD.

[2]  Hsinchun Chen,et al.  Recommendation as link prediction in bipartite graphs: A graph kernel-based machine learning approach , 2013, Decis. Support Syst..

[3]  John D. Lafferty,et al.  Information retrieval as statistical translation , 1999, SIGIR '99.

[4]  Fatemeh Pourgholamali.  Mining Information for the Cold-Item Problem , 2016, RecSys.

[5]  Siti Mariyam Shamsuddin,et al.  Deep learning-based sentiment classification of evaluative text based on Multi-feature fusion , 2019, Inf. Process. Manag..

[6]  ChengXiang Zhai,et al.  Retrieval of Relevant Opinion Sentences for New Products , 2015, SIGIR.

[7]  Cen Chen,et al.  Aspect Extraction from Product Reviews Using Category Hierarchy Information , 2017, EACL.

[8]  Wei Li,et al.  Cold Start Recommendation Based on Attribute-Fused Singular Value Decomposition , 2019, IEEE Access.

[9]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[10]  Ani Nenkova,et al.  Automatically Assessing Machine Summary Content Without a Gold Standard , 2013, CL.

[11]  Tao Chen,et al.  TriRank: Review-aware Explainable Recommendation by Modeling Aspects , 2015, CIKM.

[12]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[13]  Xiaohua Hu,et al.  Product review summarization through question retrieval and diversification , 2017, Information Retrieval Journal.

[14]  Asit Kumar Das,et al.  Graph-Based Text Summarization Using Modified TextRank , 2018, Soft Computing in Data Analytics.

[15]  Vijayan K. Asari,et al.  The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches , 2018, ArXiv.

[16]  Weitong Chen,et al.  Learning Graph-based POI Embedding for Location-based Recommendation , 2016, CIKM.

[17]  Feras Al-Obeidat,et al.  Topic and sentiment aware microblog summarization for twitter , 2018, Journal of Intelligent Information Systems.

[18]  Zhipeng Zhang,et al.  Addressing Complete New Item Cold-Start Recommendation: A Niche Item-Based Collaborative Filtering via Interrelationship Mining , 2019, Applied Sciences.

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

[20]  Fuzhen Zhuang,et al.  QPLSA: Utilizing quad-tuples for aspect identification and rating , 2015, Inf. Process. Manag..

[21]  Deng Cai,et al.  Addressing the Item Cold-Start Problem by Attribute-Driven Active Learning , 2018, IEEE Transactions on Knowledge and Data Engineering.

[22]  John M. Conroy,et al.  An Assessment of the Accuracy of Automatic Evaluation in Summarization , 2012, EvalMetrics@NAACL-HLT.

[23]  Mejari Kumar,et al.  Connecting Social Media to E-Commerce: Cold-Start Product Recommendation using Microblogging Information , 2018 .

[24]  Yehuda Koren,et al.  Collaborative filtering with temporal dynamics , 2009, KDD.

[25]  Mingzhe Wang,et al.  LINE: Large-scale Information Network Embedding , 2015, WWW.

[26]  Mohsen Kahani,et al.  Embedding unstructured side information in product recommendation , 2017, Electron. Commer. Res. Appl..

[27]  Philip S. Yu,et al.  Leveraging Meta-path based Context for Top- N Recommendation with A Neural Co-Attention Model , 2018, KDD.

[28]  Tat-Seng Chua,et al.  Attentive Aspect Modeling for Review-Aware Recommendation , 2018, ACM Trans. Inf. Syst..

[29]  Edward C. Malthouse,et al.  The Value of Online Customer Reviews , 2016, RecSys.

[30]  Sophie Ahrens,et al.  Recommender Systems , 2012 .

[31]  William W. Cohen,et al.  TransNets: Learning to Transform for Recommendation , 2017, RecSys.

[32]  Xu Chen,et al.  Joint Representation Learning for Top-N Recommendation with Heterogeneous Information Sources , 2017, CIKM.

[33]  Sang Ho Lee,et al.  An Improved Computation of the PageRank Algorithm , 2002, ECIR.

[34]  Santanu Kumar Rath,et al.  Document-level sentiment classification using hybrid machine learning approach , 2017, Knowledge and Information Systems.

[35]  Dragomir R. Radev,et al.  Centroid-based summarization of multiple documents , 2004, Inf. Process. Manag..

[36]  Mo Yu.  Factor-based Compositional Embedding Models , 2014 .

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

[38]  Yiqun Liu,et al.  Rating-Boosted Latent Topics: Understanding Users and Items with Ratings and Reviews , 2016, IJCAI.

[39]  Alessandro Bozzon,et al.  Recurrent knowledge graph embedding for effective recommendation , 2018, RecSys.

[40]  Ehsan Asgarian,et al.  The Impact of Sentiment Features on the Sentiment Polarity Classification in Persian Reviews , 2018, Cognitive Computation.

[41]  Radoslaw Nielek,et al.  Influence of consumer reviews on online purchasing decisions in older and younger adults , 2018, Decis. Support Syst..

[42]  Sanghwan Bae,et al.  Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations , 2018, AAAI.

[43]  Rada Mihalcea,et al.  TextRank: Bringing Order into Text , 2004, EMNLP.

[44]  Qin Lu,et al.  Applying regression models to query-focused multi-document summarization , 2011, Inf. Process. Manag..

[45]  Philip S. Yu,et al.  Heterogeneous Information Network Embedding for Recommendation , 2017, IEEE Transactions on Knowledge and Data Engineering.

[46]  Martin Ester,et al.  The FLDA model for aspect-based opinion mining: addressing the cold start problem , 2013, WWW.

[47]  W. Bruce Croft,et al.  A Language Modeling Approach to Information Retrieval , 1998, SIGIR Forum.

[48]  Jure Leskovec,et al.  Hidden factors and hidden topics: understanding rating dimensions with review text , 2013, RecSys.

[49]  Ding Xiao,et al.  Coupled matrix factorization and topic modeling for aspect mining , 2018, Inf. Process. Manag..

[50]  S. Chitrakala,et al.  A survey on extractive text summarization , 2017, 2017 International Conference on Computer, Communication and Signal Processing (ICCCSP).