%0 Conference Paper %1 wang2018explainable %A Wang, Nan %A Wang, Hongning %A Jia, Yiling %A Yin, Yue %B The 41st International ACM SIGIR Conference on Research &\#38; Development in Information Retrieval %C New York, NY, USA %D 2018 %I ACM %K explainable learning multitask recommendation %P 165--174 %R 10.1145/3209978.3210010 %T Explainable Recommendation via Multi-Task Learning in Opinionated Text Data %U http://doi.acm.org/10.1145/3209978.3210010 %X Explaining automatically generated recommendations allows users to make more informed and accurate decisions about which results to utilize, and therefore improves their satisfaction. In this work, we develop a multi-task learning solution for explainable recommendation. Two companion learning tasks of user preference modeling for recommendation and opinionated content modeling for explanation are integrated via a joint tensor factorization. As a result, the algorithm predicts not only a user's preference over a list of items, i.e., recommendation, but also how the user would appreciate a particular item at the feature level, i.e., opinionated textual explanation. Extensive experiments on two large collections of Amazon and Yelp reviews confirmed the effectiveness of our solution in both recommendation and explanation tasks, compared with several existing recommendation algorithms. And our extensive user study clearly demonstrates the practical value of the explainable recommendations generated by our algorithm. %@ 978-1-4503-5657-2

@inproceedings{wang2018explainable, abstract = {Explaining automatically generated recommendations allows users to make more informed and accurate decisions about which results to utilize, and therefore improves their satisfaction. In this work, we develop a multi-task learning solution for explainable recommendation. Two companion learning tasks of user preference modeling for recommendation and opinionated content modeling for explanation are integrated via a joint tensor factorization. As a result, the algorithm predicts not only a user's preference over a list of items, i.e., recommendation, but also how the user would appreciate a particular item at the feature level, i.e., opinionated textual explanation. Extensive experiments on two large collections of Amazon and Yelp reviews confirmed the effectiveness of our solution in both recommendation and explanation tasks, compared with several existing recommendation algorithms. And our extensive user study clearly demonstrates the practical value of the explainable recommendations generated by our algorithm.}, acmid = {3210010}, added-at = {2019-06-05T22:00:01.000+0200}, address = {New York, NY, USA}, author = {Wang, Nan and Wang, Hongning and Jia, Yiling and Yin, Yue}, biburl = {https://www.bibsonomy.org/bibtex/25811dcd1ff4238f67b962d582e0affa3/nosebrain}, booktitle = {The 41st International ACM SIGIR Conference on Research \&\#38; Development in Information Retrieval}, description = {Explainable Recommendation via Multi-Task Learning in Opinionated Text Data}, doi = {10.1145/3209978.3210010}, interhash = {fa4591463f6a33e3522bef3d9ec35d80}, intrahash = {5811dcd1ff4238f67b962d582e0affa3}, isbn = {978-1-4503-5657-2}, keywords = {explainable learning multitask recommendation}, location = {Ann Arbor, MI, USA}, numpages = {10}, pages = {165--174}, publisher = {ACM}, series = {SIGIR '18}, timestamp = {2019-06-05T22:00:01.000+0200}, title = {Explainable Recommendation via Multi-Task Learning in Opinionated Text Data}, url = {http://doi.acm.org/10.1145/3209978.3210010}, year = 2018 }