Rating prediction by exploring user’s preference and sentiment

Ma, Xiang; Lei, Xiaojiang; Zhao, Guoshuai; Qian, Xueming

doi:10.1007/s11042-017-4550-z

Cited by 26 publications

(10 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A new approach to combine three factors such as the user's own social sentiment which reflects his/her preference, interpersonal sentiment which creates an influence among like-minded users, and reputation of the item which reflects user's evaluation was proposed in [7] for improving the prediction accuracy. A probabilistic matrix factorization-based RS model which fully explores user reviews was proposed in [8]. User preferences, social sentiment of the user, and interpersonal influence from reviews are fused into the proposed model to make accurate predictions.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Integrated topic modeling and sentiment analysis: a review rating prediction approach for recommender systems

Mahadevan¹,

Arock²

2020

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Recommender systems (RSs) are running behind E-commerce websites to recommend items that are likely to be bought by users. Most of the existing RSs are relying on mere star ratings while making recommendations.However, ratings alone cannot help RSs make accurate recommendations, as they cannot properly capture sentiments expressed towards various aspects of the items. The other rich and expressive source of information available that can help make accurate recommendations is user reviews. Because of their voluminous nature, reviews lead to the information overloading problem. Hence, drawing out the user opinion from reviews is a decisive job. Therefore, this paper aims to build a review rating prediction model that simultaneously captures the topics and sentiments present in the reviews which are then used as features for the rating prediction. A new sentiment-enriched and topic-modeling-based review rating prediction technique which can recognize modern review contents is proposed to facilitate this feature. Experimental results show that the proposed model best infers the rating from reviews by harnessing the vital information present in them.

show abstract

Section: Related Workmentioning

confidence: 99%

“…7 R3 Representation of recommendation with short review: an approach to gear up the information available in short reviews by constructing the word vector representations of users and items [18]. 8 LDA only The proposed model without using sentiment score.…”

Section: Baselinesmentioning

confidence: 99%

Integrated topic modeling and sentiment analysis: a review rating prediction approach for recommender systems

Mahadevan¹,

Arock²

2020

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

show abstract

“…where N denotes the number of ratings between users and items. A lower RMSE (equation (13)) and a lower MAE (equation 14) correspond to a better recommendation performance.…”

Section: Evaluation Criteriamentioning

confidence: 99%

“…Several deep learning-based recommender systems have been proposed. Yet, most of them [10][11][12][13][14] were usually restricted to limited data sources or learned the latent representations of users and items independently. As a result, these approaches cannot achieve fine-grained modeling of user preferences and item features.…”

Section: Introductionmentioning

confidence: 99%

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

Gan

Zhang

2020

Complexity

View full text Add to dashboard Cite

Personalized recommender systems, as effective approaches for alleviating information overload, have received substantial attention in the last decade. Learning effective latent factors plays the most important role in recommendation methods. Several recent works extracted latent factors from user-generated content such as ratings and reviews and suffered from the sparsity problem and the unbalanced distribution problem. To tackle these problems, we enrich the latent representations by incorporating user-generated content and item raw content. Deep neural networks have emerged as very appealing in learning effective representations in many applications. 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. 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 and items. Experiments conducted on the Amazon product data demonstrate that our approach outperforms multiple state-of-the-art baselines. We provide further insight into the design selections and hyperparameters of our recommendation method. In addition, we further explore the relative importance of various item metadata information on improving the rating prediction performance towards personalized product recommendation, which is extremely valuable for feature extraction in practice.

show abstract

“…Ma et al [36] presented an approach that takes into account both user preferences and sentiments to predict the rating score. Authors used a lexiconbased approach for sentiment analysis of user reviews.…”

Section: Related Workmentioning

confidence: 99%

dTrust: A Simple Deep Learning Approach for Social Recommendation

Dang

Ignat

2017

2017 IEEE 3rd International Conference on Collaboration and Internet Computing (CIC)

View full text Add to dashboard Cite

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés. dTrust: a simple deep learning approach for social recommendationQuang-Vinh Dang, Claudia-Lavinia IgnatTo cite this version: Abstract-Rating prediction is a key task of e-commerce recommendation mechanisms. Recent studies in social recommendation enhance the performance of rating predictors by taking advantage of user relationships. However, these prediction approaches mostly rely on user personal information which is a privacy threat.In this paper, we present dTrust, a simple social recommendation approach that avoids using user personal information. It relies uniquely on the topology of an anonymized trust-useritem network that combines user trust relations with user rating scores. This topology is fed into a deep feed-forward neural network. Experiments on real-world data sets showed that dTrust outperforms state-of-the-art in terms of Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) scores for both warmstart and cold-start problems.

show abstract

Rating prediction by exploring user’s preference and sentiment

Cited by 26 publications

References 60 publications

Integrated topic modeling and sentiment analysis: a review rating prediction approach for recommender systems

Integrated topic modeling and sentiment analysis: a review rating prediction approach for recommender systems

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

dTrust: A Simple Deep Learning Approach for Social Recommendation

Contact Info

Product

Resources

About