Filters








220,903 Hits in 5.6 sec

Research on BP Neural Network Recommendation Model Fusing User Reviews and Ratings

Heyong Wang, Ming Hong, Zhenqin Hong
2021 IEEE Access  
This model improves the structure of BP neural network by specially designing the structure of network layers.  ...  User reviews and ratings can be processed in two separate sub-networks respectively and further fused in the fusion layer.  ...  The BP neural network can be divided into three layers, that is, input layer, hidden layer and output layer. A deep BP neural network usually has multiple hidden layers.  ... 
doi:10.1109/access.2021.3080079 fatcat:s3vu3bhkxbfmhfhzj7bp5euzzm

Applying Internet information technology combined with deep learning to tourism collaborative recommendation system

Meng Wang
2020 PLoS ONE  
The model accuracy is the highest with 40 hidden factors, 100 convolutions, and a 100+50 combination hidden layer.  ...  The Convolutional Neural Network (CNN) is used to process review information of users and tourism service items.  ...  Fig 5 shows that the model is divided into three parts: review information network of tourists; review information network of tourism service items; and other information networks.  ... 
doi:10.1371/journal.pone.0240656 pmid:33271589 pmcid:PMC7714558 fatcat:v64dhfak7bgyrauvupdratsv4a

DeepFusion: Fusing User-Generated Content and Item Raw Content towards Personalized Product Recommendation

Mingxin Gan, Hang Zhang
2020 Complexity  
In this framework, we utilize multiple types of deep neural networks that are best suited for each type of heterogeneous inputs and introduce an extra layer to obtain the joint representations for users  ...  In this paper, we propose a novel deep neural architecture named DeepFusion to jointly learn user and item representations from numerical ratings, textual reviews, and item metadata.  ...  A popular research line is the joint modeling of numerical ratings and textual reviews for recommendation. Textual reviews are able to express user opinions towards various item features.  ... 
doi:10.1155/2020/4780191 fatcat:r5pixfcteze3hi46bdouxjnlp4

Fusing User Reviews Into Heterogeneous Information Network Recommendation Model

Xu Chen, Jingjing Tian, Xinxin Tian, Shudong Liu
2022 IEEE Access  
However, most of the current recommendation models fail to make the most of the ample resources hidden behind auxiliary data and user reviews. For this reason, we put forward the FHRec model.  ...  As an effective method to deal with this dilemma of information overload, recommendation system has become a popular area of research for the past few years.  ...  Specifically, through a two-layer neural network learning attention scores for the features learned from different meta-paths and the features extracted from reviews.  ... 
doi:10.1109/access.2022.3176727 fatcat:n5s435ezezfgffjkcinc4oug5u

Customer Reviews Analysis with Deep Neural Networks for E-Commerce Recommender Systems

Babak Maleki Shoja, Nasseh Tabrizi
2019 IEEE Access  
Then, we employed a deep neural network to extract deep features from the reviews-characteristics matrix to deal with sparsity, ambiguity, and redundancy.  ...  Written customer review is a rich source of information that can offer insights into the recommender system.  ...  In order to transform this architecture into an autoencoder using a deep neural network, we need to use more layers as hidden layers where the output of each layer is the input for the next layer.  ... 
doi:10.1109/access.2019.2937518 fatcat:kmqunio5jrahnkgpupin5lfbta

Joint Deep Model with Multi-Level Attention and Hybrid-Prediction for Recommendation

Zhipeng Lin, Yuhua Tang, Yongjun Zhang
2019 Entropy  
Based on these two designs, we build a Multi-level Attentional and Hybrid-prediction-based Recommender (MAHR) model for recommendation.  ...  However, it is still a challenge for RS to extract the most informative feature from a tremendous amount of reviews.  ...  In the future, we plan to combine the transfer learning and the latent factor model to build a more robust prediction layer for recommender system.  ... 
doi:10.3390/e21020143 pmid:33266859 fatcat:xtj7vkbk6fgebaqytfgj5j2xvm

Joint Deep Modeling of Users and Items Using Reviews for Recommendation [article]

Lei Zheng, Vahid Noroozi, Philip S. Yu
2017 arXiv   pre-print
The proposed model, named Deep Cooperative Neural Networks (DeepCoNN), consists of two parallel neural networks coupled in the last layers.  ...  A shared layer is introduced on the top to couple these two networks together.  ...  We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan X GPU used for this research.  ... 
arXiv:1701.04783v1 fatcat:jfdnrashgzeq7pa4dtmbvtmyhy

Joint Deep Network With Auxiliary Semantic Learning for Popular Recommendation

Xingkai Wang, Yiqiang Sheng, Haojiang Deng
2020 IEEE Access  
In this paper, we propose a new joint deep network model with auxiliary semantic learning for the popular recommendation algorithm (DMPRA).  ...  First, we define the items with a large quantity of review data and high ratings as the popular recommended items. Second, we introduce text analysis into the popular recommendation algorithm.  ...  ACKNOWLEDGMENT The authors would like to thank the editor and the anonymous reviewers for constructive suggestions.  ... 
doi:10.1109/access.2020.2976498 fatcat:7y5kidjvzfdzzhm5qfv35h7hjm

A Parallel Deep Neural Network Using Reviews and Item Metadata for Cross-domain Recommendation

Wenxing Hong, Nannan Zheng, Ziang Xiong, Zhiqiang Hu
2020 IEEE Access  
CD-DNN builds a single mapping for user features in the latent space, so that the network for user is optimized together with item features from other domains.  ...  In this paper, we propose Crossdomain Deep Neural Network (CD-DNN) for the cross-domain recommendation.  ...  In the next three subsections, we only focus on introducing the process for the network Net u because the networks of Net u and Net i are almost identical; they differ only in input. 1) EMBEDDING LAYER  ... 
doi:10.1109/access.2020.2977123 fatcat:4lfqtfpt4jdplf2j66do2p325y

Recommendation algorithm combining ratings and comments

Xujian Fang, Jiayi Wang, Dewen Seng, Binquan Li, Chenxuan Lai, Xiyuan Chen
2021 Alexandria Engineering Journal  
feature vector; finally, it is fed into a factorization machine and a fully connected network for scoring prediction.  ...  The rating data of recommendation systems are too sparse, and many existing studies introduce review information to alleviate this phenomenon, but the connection between reviews and the importance of each  ...  learning approach for modeling reviews, using two parallel convolutional neural networks for feature extraction of user-item reviews separately, and then feeding the obtained features into a factorization  ... 
doi:10.1016/j.aej.2021.04.056 fatcat:3cnjrvyjrbauxoykoir5gxpuq4

Review-Based Cross-Domain Collaborative Filtering: A Neural Framework

Thanh-Nam Doan, Shaghayegh Sahebi
2019 ACM Conference on Recommender Systems  
Most current crossdomain recommenders focus on modeling user ratings but pay limited attention to user reviews.  ...  CCS CONCEPTS • Information systems → Recommender systems; • Computing methodologies → Neural networks.  ...  hybrid model unifies both ratings and reviews under a neural framework. • Cross-domain neural network (CDN) [3] : This model utilizes neural networks for cross domain recommendation system.  ... 
dblp:conf/recsys/DoanS19 fatcat:u4cj7f2f55d57ojmstaw6jsufq

Deep Personalized Medical Recommendations Based on the Integration of Rating Features and Review Sentiment Analysis

Qihang Zhou, Lei Su, Liping Wu, Di Jiang, Yin Zhang
2021 Wireless Communications and Mobile Computing  
In this paper, we propose a personalized medical recommendation method based on a convolutional neural network that integrates revised ratings and review text, called revised rating and review based on  ...  a convolutional neural network (RR&R-CNN).  ...  In the input layer of the convolutional neural network model, a user's review text of doctors and the revised rating are combined as input features.  ... 
doi:10.1155/2021/5551318 fatcat:ultkhl7mlrdzbgzo63at7l6fr4

A Heterogeneous Graph Neural Model for Cold-start Recommendation

Siwei Liu, Iadh Ounis, Craig Macdonald, Zaiqiao Meng
2020 Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval  
A Heterogeneous Graph Neural Model for Cold-start Recommendation . In  ...  predicted from the social network and textual reviews.  ...  For a fair comparison, we set the number of neural network layers of the models including NeuMF, NGCF and HGNR to 3.  ... 
doi:10.1145/3397271.3401252 dblp:conf/sigir/LiuOMM20 fatcat:pcogjke2ivgg5bfbxrbirkunuy

Hierarchical User and Item Representation with Three-Tier Attention for Recommendation

Chuhan Wu, Fangzhao Wu, Junxin Liu, Yongfeng Huang
2019 Proceedings of the 2019 Conference of the North  
In addition, we incorporate a three-tier attention network in our model to select important words, sentences and reviews.  ...  In this paper, we propose a hierarchical user and item representation model with threetier attention to learn user and item representations from reviews for recommendation.  ...  Conclusion In this paper, we propose a hierarchical user and item representation model with three-tier attention to learn user and item representations from reviews for recommendation.  ... 
doi:10.18653/v1/n19-1180 dblp:conf/naacl/WuWLH19 fatcat:rjccuuj6s5hu7kw4dagjlxbovq

Sentiment Neural Network(SNN)-for Knowledge based Recommender System

2019 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
A novel Sentiment Neural Network along with knowledge recommender system is suggested for review features extraction, text classification and analyzing review features in the various domains.  ...  In this way deep learning play an increasingly vital role in review recommender systems, since they used a bunch of discrete values for review. However, a problem arises regarding that feedbacks.  ...  The predictive model design for the SNN excellence creates planned usage of Review related data in text form. The SNN input and output layers functionality and forward neural network is the similar.  ... 
doi:10.35940/ijitee.a4196.129219 fatcat:zkjq7rsbsbgpfcs2d67bercxhi
« Previous Showing results 1 — 15 out of 220,903 results