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.
%0 Generic
%1 zheng2017joint
%A Zheng, Lei
%A Noroozi, Vahid
%A Yu, Philip S.
%D 2017
%K review
%T Joint Deep Modeling of Users and Items Using Reviews for Recommendation
%U http://arxiv.org/abs/1701.04783
%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.
@conference{zheng2017joint,
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.},
added-at = {2017-05-08T00:28:08.000+0200},
author = {Zheng, Lei and Noroozi, Vahid and Yu, Philip S.},
biburl = {https://www.bibsonomy.org/bibtex/214619c2d8abba73e3f652d641210f7e0/dennis-},
interhash = {287d1797abc8253ae6e53673ae425747},
intrahash = {14619c2d8abba73e3f652d641210f7e0},
keywords = {review},
note = {cite arxiv:1701.04783Comment: WSDM 2017},
timestamp = {2017-05-08T00:28:08.000+0200},
title = {Joint Deep Modeling of Users and Items Using Reviews for Recommendation},
url = {http://arxiv.org/abs/1701.04783},
year = 2017
}