{"type":"ScholarlyArticle","title":"Synthesizing Aspect-Driven Recommendation Explanations from Reviews","authors":[{"name":"Trung-Hoang Le","slug":"trung-hoang-le","given":"Trung-Hoang","family":"Le","affiliation":"Singapore Management University , Singapore"},{"name":"Hady W. Lauw","slug":"hady-w-lauw","given":"Hady W.","family":"Lauw","affiliation":"Singapore Management University , Singapore"}],"abstract":"Explanations help users make sense of recommendations, increasing the likelihood of adoption. Existing approaches to explainable recommendations tend to rely on rigidly standardized templates, only allowing fill-in-the-blank aspect-level sentiments. For more flexible, literate, and varied explanations that cover various aspects of interest, we propose to synthesize an explanation by selecting snippets from reviews to optimize representativeness and coherence.  To fit the target user's aspect preferences, we contextualize the opinions based on a compatible explainable recommendation model. Experiments on datasets of varying product categories showcase the efficacies of our method as compared to baselines based on templates, review summarization, selection, and text generation.","doi":"10.24963/ijcai.2020/336","url":"https://ijcai.org/proceedings/2020/336","pdf":"https://ijcai.org/proceedings/2020/0336.pdf","markdown":"https://ijcai.org/proceedings/2020/336.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/336","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Machine Learning","track":"Main track","number":336,"pages":{"first":2427,"last":2434},"keywords":["Machine Learning: Interpretability","Data Mining: Mining Text, Web, Social Media"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/25338/file_25338.m3u8","length_sec":293,"provider":"hls"}],"references":[{"position":1,"raw":"[Barrios et al., 2016] Federico Barrios, Federico López, Luis Arg- erich, and Rosa Wachenchauzer. Variations of the similar- ity function of textrank for automated summarization. CoRR, abs/1602.03606, 2016.","title":"Variations of the similarity function of textrank for automated summarization","authors":"Federico Barrios, Federico López, Luis Argerich, Rosa Wachenchauzer","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bauman et al., 2017] Konstantin Bauman, Bing Liu, and Alexan- der Tuzhilin. Aspect based recommendations: Recommending items with the most valuable aspects based on user reviews. In KDD, pages 717-725, New York, NY, USA, 2017. ACM.","title":"Aspect based recommendations: Recommending items with the most valuable aspects based on user reviews","authors":"Konstantin Bauman, Bing Liu, Alexander Tuzhilin","year":"2017","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2016] Xu Chen, Zheng Qin, Yongfeng Zhang, and Tao Xu. Learning to rank features for recommendation over multiple categories. In SIGIR, SIGIR '16, pages 305-314, New York, NY, USA, 2016. ACM.","title":"Learning to rank features for recommendation over multiple categories","authors":"Zheng Xu Chen, Yongfeng Qin, Tao Zhang, Xu","year":"2016","venue":"SIGIR, SIGIR '16","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2017] Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Si Wei, Hui Jiang, and Diana Inkpen. Enhanced LSTM for nat- ural language inference. In ACL, pages 1657-1668, Vancouver, Canada, 2017. ACL.","title":"Enhanced LSTM for natural language inference","authors":"Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Si Wei, Hui Jiang, Diana Inkpen","year":"2017","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2019] Zhongxia Chen, Xiting Wang, Xing Xie, Tong Wu, Guoqing Bu, Yining Wang, and Enhong Chen. Co-attentive multi-task learning for explainable recommendation. In IJCAI, pages 2137-2143. AAAI Press, 2019.","title":"Co-attentive multi-task learning for explainable recommendation","authors":"Zhongxia Chen, Xiting Wang, Xing Xie, Tong Wu, Guoqing Bu, Yining Wang, Enhong Chen","year":"2019","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2019/296"},{"position":6,"raw":"[Cornuéjols et al., 1983] Gérard Cornuéjols, George L Nemhauser, and Lairemce A Wolsey. The uncapacitated facility location problem. Technical report, Carnegie-mellon univ pittsburgh pa management sciences research group, 1983.","title":"The uncapacitated facility location problem","authors":"Gérard Cornuéjols, George L Nemhauser, Lairemce A Wolsey","year":"1983","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Dong et al., 2017] Li Dong, Shaohan Huang, Furu Wei, Mirella Lapata, Ming Zhou, and Ke Xu. Learning to generate product reviews from attributes. In EACL, volume 1, pages 623-632, 2017.","title":"Learning to generate product reviews from attributes","authors":"Li Dong, Shaohan Huang, Furu Wei, Mirella Lapata, Ming Zhou, Ke Xu","year":"2017","venue":"EACL","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Gao et al., 2019] Jingyue Gao, Xiting Wang, Yasha Wang, and Xing Xie. Explainable recommendation through attentive multi- view learning. In AAAI, volume 33, pages 3622-3629, 2019.","title":"Explainable recommendation through attentive multiview learning","authors":"Jingyue Gao, Xiting Wang, Yasha Wang, Xing Xie","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Golab et al., 2015] Lukasz Golab, Flip Korn, Feng Li, Barna Saha, and Divesh Srivastava. Size-constrained weighted set cover. In ICDE, pages 879-890. IEEE, 2015.","title":"Size-constrained weighted set cover","authors":"Lukasz Golab, Flip Korn, Feng Li, Barna Saha, Divesh Srivastava","year":"2015","venue":"ICDE","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[He et al., 2015] Xiangnan He, Tao Chen, Min-Yen Kan, and Xiao Chen. Trirank: Review-aware explainable recommendation by modeling aspects. In CIKM, CIKM '15, pages 1661-1670, New York, NY, USA, 2015. ACM.","title":"Trirank: Review-aware explainable recommendation by modeling aspects","authors":"He","year":"2015","venue":"CIKM, CIKM '15","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hochbaum, 1982] Dorit S Hochbaum. Heuristics for the fixed cost median problem. Math. Program., 22(1):148-162, 1982.","title":"Heuristics for the fixed cost median problem","authors":"Dorit S Hochbaum","year":"1982","venue":"Math. Program","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kolda and Bader, 2009] Tamara G Kolda and Brett W Bader. Ten- sor decompositions and applications. SIAM review, 51(3):455- 500, 2009.","title":"Tensor decompositions and applications","authors":"G Tamara, Brett W Kolda, Bader","year":"2009","venue":"SIAM review","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lan and Xu, 2018] Wuwei Lan and Wei Xu. Neural network mod- els for paraphrase identification, semantic textual similarity, nat- ural language inference, and question answering. In COLING, pages 3890-3902, 2018.","title":"Neural network models for paraphrase identification, semantic textual similarity, natural language inference, and question answering","authors":"Lan, Xu ; ] Wuwei Lan, Wei Xu","year":"2018","venue":"COLING","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Lappas et al., 2012] Theodoros Lappas, Mark Crovella, and Evi- maria Terzi. Selecting a characteristic set of reviews. In KDD, pages 832-840. ACM, 2012.","title":"Selecting a characteristic set of reviews","authors":"Theodoros Lappas, Mark Crovella, Evimaria Terzi","year":"2012","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Li et al., 2017] Piji Li, Zihao Wang, Zhaochun Ren, Lidong Bing, and Wai Lam. Neural rating regression with abstractive tips gen- eration for recommendation. In SIGIR, page 345-354, New York, NY, USA, 2017. Association for Computing Machinery.","title":"Neural rating regression with abstractive tips generation for recommendation","authors":"Li","year":"2017","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lin and Hovy, 2003] Chin-Yew Lin and Eduard Hovy. Automatic evaluation of summaries using n-gram co-occurrence statistics. In NAACL, pages 71-78, Stroudsburg, PA, USA, 2003. ACL.","title":"Automatic evaluation of summaries using n-gram co-occurrence statistics","authors":"Lin, Hovy ; Chin-Yew Lin, Eduard Hovy","year":"2003","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Lu et al., 2018] Yichao Lu, Ruihai Dong, and Barry Smyth. Why i like it: Multi-task learning for recommendation and explanation. In RecSys, page 4-12, New York, NY, USA, 2018. ACM.","title":"Why i like it: Multi-task learning for recommendation and explanation","authors":"Lu","year":"2018","venue":"RecSys","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ma et al., 2019] Weizhi Ma, Min Zhang, Yue Cao, Woojeong Jin, Chenyang Wang, Yiqun Liu, Shaoping Ma, and Xiang Ren. Jointly learning explainable rules for recommendation with knowledge graph. In WWW, WWW '19, pages 1210-1221, New York, NY, USA, 2019. ACM.","title":"Jointly learning explainable rules for recommendation with knowledge graph","authors":"Ma","year":"2019","venue":"WWW, WWW '19","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[McAuley et al., 2015] Julian McAuley, Christopher Targett, Qin- feng Shi, and Anton van den Hengel. Image-based recommen- dations on styles and substitutes. In SIGIR, pages 43-52, New York, NY, USA, 2015. ACM.","title":"Image-based recommendations on styles and substitutes","authors":"Julian Mcauley, Christopher Targett, Qinfeng Shi, Anton Van Den, Hengel","year":"2015","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Melamud et al., 2016] Oren Melamud, Jacob Goldberger, and Ido Dagan. context2vec: Learning generic context embedding with bidirectional lstm. In CoNLL, pages 51-61, 2016.","title":"context2vec: Learning generic context embedding with bidirectional lstm","authors":"Oren Melamud, Jacob Goldberger, Ido Dagan","year":"2016","venue":"CoNLL","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Ni and McAuley, 2018] Jianmo Ni and Julian McAuley. Person- alized review generation by expanding phrases and attending on aspect-aware representations. In ACL, volume 2, pages 706-711, 2018.","title":"Jianmo Ni and Julian McAuley. Personalized review generation by expanding phrases and attending on aspect-aware representations","authors":"Mcauley Ni","year":"2018","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Ni et al., 2019] Jianmo Ni, Jiacheng Li, and Julian McAuley. Justi- fying recommendations using distantly-labeled reviews and fine- grained aspects. In EMNLP, pages 188-197. ACL, 2019.","title":"Justifying recommendations using distantly-labeled reviews and finegrained aspects","authors":"Ni","year":"2019","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Nie and Bansal, 2017] Yixin Nie and Mohit Bansal. Shortcut- stacked sentence encoders for multi-domain inference. In RepE- val, pages 41-45, Copenhagen, Denmark, 2017. Association for Computational Linguistics.","title":"Shortcutstacked sentence encoders for multi-domain inference","authors":"Bansal Nie, Yixin Nie, Mohit Bansal","year":"2017","venue":"RepEval","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Ren et al., 2017] Zhaochun Ren, Shangsong Liang, Piji Li, Shuaiqiang Wang, and Maarten de Rijke. Social collabora- tive viewpoint regression with explainable recommendations. In WSDM, pages 485-494, New York, NY, USA, 2017. ACM.","title":"Social collaborative viewpoint regression with explainable recommendations","authors":"Ren","year":"2017","venue":"WSDM","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Sun et al., 2013] Huan Sun, Alex Morales, and Xifeng Yan. Syn- thetic review spamming and defense. In KDD, pages 1088-1096. ACM, 2013.","title":"Synthetic review spamming and defense","authors":"Huan Sun, Alex Morales, Xifeng Yan","year":"2013","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Tan et al., 2016] Yunzhi Tan, Min Zhang, Yiqun Liu, and Shaop- ing Ma. Rating-boosted latent topics: Understanding users and items with ratings and reviews. In IJCAI, volume 16, pages 2640- 2646, 2016.","title":"Rating-boosted latent topics: Understanding users and items with ratings and reviews","authors":"Tan","year":"2016","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2016/375"},{"position":27,"raw":"[Truong and Lauw, 2019] Quoc-Tuan Truong and Hady Lauw. Multimodal review generation for recommender systems. In WWW, pages 1864-1874, New York, NY, USA, 2019. ACM.","title":"Multimodal review generation for recommender systems","authors":"Quoc-Tuan Truong, Hady Lauw","year":"2019","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Tsaparas et al., 2011] Panayiotis Tsaparas, Alexandros Ntoulas, and Evimaria Terzi. Selecting a comprehensive set of reviews. In KDD, pages 168-176, New York, NY, USA, 2011. ACM.","title":"Selecting a comprehensive set of reviews","authors":"Panayiotis Tsaparas, Alexandros Ntoulas, Evimaria Terzi","year":"2011","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Wang et al., 2018a] Nan Wang, Hongning Wang, Yiling Jia, and Yue Yin. Explainable recommendation via multi-task learning in opinionated text data. In SIGIR, SIGIR '18, pages 165-174, New York, NY, USA, 2018. ACM.","title":"Explainable recommendation via multi-task learning in opinionated text data","authors":"Wang","year":"2018","venue":"SIGIR, SIGIR '18","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Wang et al., 2018b] Xiting Wang, Yiru Chen, Jie Yang, Le Wu, Zhengtao Wu, and Xing Xie. A reinforcement learning frame- work for explainable recommendation. In ICDM, pages 587-596. IEEE, 2018.","title":"A reinforcement learning framework for explainable recommendation","authors":"Wang","year":"2018","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Wu and Ester, 2015] Yao Wu and Martin Ester. Flame: A proba- bilistic model combining aspect based opinion mining and col- laborative filtering. In WSDM, WSDM '15, pages 199-208, New York, NY, USA, 2015. ACM.","title":"Flame: A probabilistic model combining aspect based opinion mining and collaborative filtering","authors":"Ester ; ] Yao Wu, Martin Wu, Ester","year":"2015","venue":"WSDM, WSDM '15","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhang et al., 2014] Yongfeng Zhang, Guokun Lai, Min Zhang, Yi Zhang, Yiqun Liu, and Shaoping Ma. Explicit factor models for explainable recommendation based on phrase-level sentiment analysis. In SIGIR, SIGIR '14, pages 83-92, New York, NY, USA, 2014. ACM.","title":"Explicit factor models for explainable recommendation based on phrase-level sentiment analysis","authors":"Yongfeng Zhang, Guokun Lai, Min Zhang, Yi Zhang, Yiqun Liu, Shaoping Ma","year":"2014","venue":"SIGIR, SIGIR '14","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}