Joint Deep Modeling of Users and Items Using Reviews for Recommendation
arXiv:1701.04783
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.
arXiv commentWSDM 2017
References in corpus (4)
Cited by in corpus (31)
- DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
- Learning over Knowledge-Base Embeddings for Recommendation
- Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation
- Neural Rating Regression with Abstractive Tips Generation for Recommendation
- Aspect-Aware Latent Factor Model: Rating Prediction with Ratings and Reviews
- ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation
- Use of Deep Learning in Modern Recommendation System: A Summary of Recent Works
- A Hybrid Recommender System for Recommending Smartphones to Prospective Customers
- Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-Time
- Perceive Your Users in Depth: Learning Universal User Representations from Multiple E-commerce Tasks
- NeuRec: On Nonlinear Transformation for Personalized Ranking
- SIFN: A Sentiment-aware Interactive Fusion Network for Review-based Item Recommendation
- Improving Explainable Recommendations with Synthetic Reviews
- A Context-Aware User-Item Representation Learning for Item Recommendation
- MARS: Memory Attention-Aware Recommender System
- Variational Collaborative Learning for User Probabilistic Representation
- Deep Heterogeneous Autoencoders for Collaborative Filtering
- Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding
- Contaminant Removal for Android Malware Detection Systems
- T-RECS: A Simulation Tool to Study the Societal Impact of Recommender Systems
- Probabilistic Ensemble of Collaborative Filters
- Multi-Level Deep Cascade Trees for Conversion Rate Prediction in Recommendation System
- A Hierarchical Self-attentive Convolution Network for Review Modeling in Recommendation Systems
- Deep Multi-view Models for Glitch Classification
- PERS: A Personalized and Explainable POI Recommender System
- AI-Powered Text Generation for Harmonious Human-Machine Interaction: Current State and Future Directions
- Asymmetrical Hierarchical Networks with Attentive Interactions for Interpretable Review-Based Recommendation
- Representation Learning by Reconstructing Neighborhoods
- GEMRank: Global Entity Embedding For Collaborative Filtering
- Gated Attentive-Autoencoder for Content-Aware Recommendation
- A collaborative filtering model with heterogeneous neural networks for recommender systems