%0 Conference Paper %1 Zheng:2017:JDM:3018661.3018665 %A Zheng, Lei %A Noroozi, Vahid %A Yu, Philip S. %B Proceedings of the Tenth ACM International Conference on Web Search and Data Mining %C New York, NY, USA %D 2017 %I ACM %K final thema:neural_attentional_rating_regression %P 425--434 %R 10.1145/3018661.3018665 %T Joint Deep Modeling of Users and Items Using Reviews for Recommendation %U http://doi.acm.org/10.1145/3018661.3018665 %X A large amount of information exists in reviews written by users. This source of information has been ignored by most of the current recommender systems while it can potentially alleviate the sparsity problem and improve the quality of recommendations. In this paper, we present a deep model to learn item properties and user behaviors jointly from review text. The proposed model, named Deep Cooperative Neural Networks (DeepCoNN), consists of two parallel neural networks coupled in the last layers. One of the networks focuses on learning user behaviors exploiting reviews written by the user, and the other one learns item properties from the reviews written for the item. A shared layer is introduced on the top to couple these two networks together. The shared layer enables latent factors learned for users and items to interact with each other in a manner similar to factorization machine techniques. Experimental results demonstrate that DeepCoNN significantly outperforms all baseline recommender systems on a variety of datasets. %@ 978-1-4503-4675-7

@inproceedings{Zheng:2017:JDM:3018661.3018665, abstract = {A large amount of information exists in reviews written by users. This source of information has been ignored by most of the current recommender systems while it can potentially alleviate the sparsity problem and improve the quality of recommendations. In this paper, we present a deep model to learn item properties and user behaviors jointly from review text. The proposed model, named Deep Cooperative Neural Networks (DeepCoNN), consists of two parallel neural networks coupled in the last layers. One of the networks focuses on learning user behaviors exploiting reviews written by the user, and the other one learns item properties from the reviews written for the item. A shared layer is introduced on the top to couple these two networks together. The shared layer enables latent factors learned for users and items to interact with each other in a manner similar to factorization machine techniques. Experimental results demonstrate that DeepCoNN significantly outperforms all baseline recommender systems on a variety of datasets.}, acmid = {3018665}, added-at = {2020-01-17T03:28:41.000+0100}, address = {New York, NY, USA}, author = {Zheng, Lei and Noroozi, Vahid and Yu, Philip S.}, biburl = {https://www.bibsonomy.org/bibtex/2d96c2f2629b3eb677223f96327bd907e/simon_diener}, booktitle = {Proceedings of the Tenth ACM International Conference on Web Search and Data Mining}, description = {This paper introduces the DeepConn approach of modeling users and items by using reviews. This technique influenced the NARRE and DER approach of Chen et al. heavily.}, doi = {10.1145/3018661.3018665}, interhash = {287d1797abc8253ae6e53673ae425747}, intrahash = {d96c2f2629b3eb677223f96327bd907e}, isbn = {978-1-4503-4675-7}, keywords = {final thema:neural_attentional_rating_regression}, location = {Cambridge, United Kingdom}, numpages = {10}, pages = {425--434}, publisher = {ACM}, series = {WSDM '17}, timestamp = {2020-01-17T03:28:41.000+0100}, title = {Joint Deep Modeling of Users and Items Using Reviews for Recommendation}, url = {http://doi.acm.org/10.1145/3018661.3018665}, year = 2017 }