Hybrid neural recommendation with joint deep representation learning of ratings and reviews

Liu, Hongtao; Wang, Yian; Peng, Qiyao; Wu, Fangzhao; Gan, Lin; Pan, Lin; Jiao, Pengfei

doi:10.1016/j.neucom.2019.09.052

Cited by 83 publications

(40 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then by employing the embedding layer, interaction features for user and item are inferred. Liu et al (2020) and Wang et al (2019) proposed a hybrid model based on neural networks to learn deep representation of users and items exploiting both ratings and reviews together. It consists of three components; one is CNN based and is used to learn user and item features from respective user and item review texts.…”

Section: Convolutional Neural Network For Rating Predictionmentioning

confidence: 99%

“…The observed variables in LSARS are users' check-in records and latent variables are topic, region, and sentiment. Wang et al (2019) and Liu et al (2020) both used hierarchical attention model that fuse latent factor model to predict the ratings i.e. utilize factor vectors of latent factor model in attention network and later combining these factors with representative features extracted from review text for producing ratings.…”

Section: Sentiment Analysis In Recommendationmentioning

confidence: 99%

“…Classification of deep neural network-based models Table 1 Publications based on different deep learning models Models Publications Autoencoders Deng et al (2016), Wang et al (2015), Dong et al (2017),Ma et al (2018), Ouyang et al (2014), Zuo et al (2016), Wu et al (2016b), Li et al (2015), Strub et al (2016), Ying et al (2016), Wei et al (2016, 2017), Sedhain et al (2015), Strub and Mary (2015), Koren (2010) CNNs Wang et al (2017b), Chu and Tsai (2017), Pan et al (2010), Zheng et al (2017), Catherine and Cohen (2017), Kim et al (2016), Tuan and Phuong (2017), Van den Oord et al (2013), He et al (2017), Wang et al (2015), Seo et al (2017), Wu et al (2019), Liu et al (2019), He and Chua (2017), Tang and Wang (2018), Rendle (2010), Liu et al (2020), Wu et al (2017c) RNNs Lu et al (2018), Wu et al (2016a), (2017b) Hidasi et al (2015), Tan et al (2016b, 2017a), Hidasi and Karatzoglou (2018), Dai et al (2016), Kim et al (2016), Li et al (2017), Xing et al (2019), Ye et al (2017) RBMs Salakhutdinov et al (2007), Gunawardana and Meek (2008), Deng et al (2016), Georgiev and Nakov (2013), Hu et al (2014), Truyen et al (2009), Liu et al (2014, 2015), Abdollahi and Nasraoui (2016), Du et al (2017), Yedder et al (2017) DBNs Wang and Wang (2014), Chen et al (2019), Yuan et al (2017), Oh et al (2014), Zhao et al (2015) MLP He et al (2017), Cheng et al (2018a), He and Chua (2017), Lian et al (2018), Liu et al (2020) NADE Larochelle and Murray (2011), Zheng et al (2016), Du et al (2018) FFNN Fu et al (2019), Zhang et al (2017), Purkaystha et al (2019) Attention based Seo et al (2017), Lu et al (2018), Wu et al (2019), Liu et al (2017, 2019), Xing et al (2019), Vaswani et al (2017), Cheng et al (2018a), He et al (2018), Wang et al (2019) Hybrid Models Seo et al (2017), Lu et al (2018), Wu et al (2019), Dong et al (2017), Ma et al (2018),Liu et al (2019Liu et al ( , 2020 …”

mentioning

confidence: 99%

See 2 more Smart Citations

Deep learning techniques for rating prediction: a survey of the state-of-the-art

et al. 2020

View full text Add to dashboard Cite

With the growth of online information, varying personalization drifts and volatile behaviors of internet users, recommender systems are effective tools for information filtering to overcome the information overload problem. Recommender systems utilize rating prediction approaches i.e. predicting the rating that a user will give to a particular item, to generate ranked lists of items according to the preferences of each user in order to make personalized recommendations. Although previous recommendation systems are effective in creating attired recommendations, however, they still suffer from different types of challenges such as accuracy, scalability, cold-start, and data sparsity. In the last few years, deep learning has attained substantial interest in various research areas such as computer vision, speech recognition, and natural language processing. Deep learning based approaches are vigorous in not only performance improvement but also to feature representations learning from the scratch. The impact of deep learning is also prevalent, recently validating its efficacy on information retrieval and recommender systems research. In this study, a comprehensive review of deep learning-based rating prediction approaches is provided to help out new researchers interested in the subject. More concretely, the classification of deep learning-based recommendation/rating prediction models is provided and articulated along with an extensive summary of the state-of-the-art. Lastly, new trends are exposited with new perspectives pertaining to this novel and exciting development of the field.

show abstract

Section: Convolutional Neural Network For Rating Predictionmentioning

confidence: 99%

Section: Sentiment Analysis In Recommendationmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Deep learning techniques for rating prediction: a survey of the state-of-the-art

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The Diffnet simulates how a user's potential embedding evolves as the social diffusion process continues [14]. The HRDR is a hybrid neural recommendation model that learns the depth representation of users and items from ratings and reviews [15]. Expressing users' long-term and short-term interests effectively is the key of next basket recommendation.…”

Section: Related Workmentioning

confidence: 99%

Next Basket Recommendation Model Based on Attribute-Aware Multi-Level Attention

Liu

Yin

2020

IEEE Access

View full text Add to dashboard Cite

Next basket recommendation is a challenging problem, mainly due to the relationships among the items in a basket almost not being considered in current research. In this paper, we address next basket recommendation with a novel deep learning architecture. In particular, we consider both the shortterm user interests and the long-term user preferences, and we design a new attention that considers the relationships among the items in a basket. We extensively evaluated the proposed model on two benchmark data sets, the Ta-Feng and JingDong datasets. The experimental results show that the proposed model outperforms several state-of-the-art next basket recommendation models. In the experiments of the modules' effects, we also verify the effectiveness of each module. The model significantly improves the NDCG by 25.5 percentage points and 5 percentage points when compared with the uncompleted network model on the JingDong and Ta-Feng datasets, respectively; while in terms of the F1, the performance is improved by 14.6 and 23.4 percentage points, respectively. INDEX TERMS Next basket recommendation, deep learning, self-attention, item attributes.

show abstract

“…At present, a large number of recommended algorithms emerge in which collaborative filtering and content-based semantic model are the more popular algorithms in the early development of recommendation systems, which have been greatly developed in the past decade [11,12]. The recommendation model based on deep learning has gradually become the hot spot of researchers in the face of the remarkable achievements of deep learning technology in many applications of artificial intelligence.…”

Section: Introductionmentioning

confidence: 99%

A hybrid recommendation model in social media based on deep emotion analysis and multi-source view fusion

et al. 2020

View full text Add to dashboard Cite

The recommendation system is an effective means to solve the information overload problem that exists in social networks, which is also one of the most common applications of big data technology. Thus, the matrix decomposition recommendation model based on scoring data has been extensively studied and applied in recent years, but the data sparsity problem affects the recommendation quality of the model. To this end, this paper proposes a hybrid recommendation model based on deep emotion analysis and multi-source view fusion which makes a personalized recommendation with user-post interaction ratings, implicit feedback and auxiliary information in a hybrid recommendation system. Specifically, the HITS algorithm is used to process the data set, which can filter out the users and posts with high influence and eliminate most of the low-quality users and posts. Secondly, the calculation method of measuring the similarity of candidate posts and the method of calculating K nearest neighbors are designed, which solves the problem that the text description information of post content in the recommendation system is difficult to mine and utilize. Then, the cooperative training strategy is used to achieve the fusion of two recommended views, which eliminates the data distribution deviation added to the training data pool in the iterative training. Finally, the performance of the DMHR algorithm proposed in this paper is compared with other state-of-art algorithms based on the Twitter dataset. The experimental results show that the DMHR algorithm has significant improvements in score prediction and recommendation performance.

show abstract

Hybrid neural recommendation with joint deep representation learning of ratings and reviews

Cited by 83 publications

References 8 publications

Deep learning techniques for rating prediction: a survey of the state-of-the-art

Deep learning techniques for rating prediction: a survey of the state-of-the-art

Next Basket Recommendation Model Based on Attribute-Aware Multi-Level Attention

A hybrid recommendation model in social media based on deep emotion analysis and multi-source view fusion

Contact Info

Product

Resources

About