Personalized recommendation based on customer preference mining and sentiment assessment from a Chinese e-commerce website

Jing, Nan; Jiang, Tao; Du, Jianjun; Sugumaran, Vijayan

doi:10.1007/s10660-017-9275-6

Cited by 33 publications

(16 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To solve this issue, the cooperative filtering systems include "social filtering" or recommender system because they are based on the opinion of the other customers [10]. The strategy merging sentiment assessment with cooperative filtering as in [7], which used to enhance the recommendation results' accuracy of customers and attempts to overcome the problem of cold start and data sparsity.…”

Section: Related Workmentioning

confidence: 99%

“…Nowadays E-commerce websites are developing so quickly, for that it is a difficult action for online buyers to select a proper category. To deal with such a broad-ranging commercial problem, most electronic retailing sites merge the Internet services with buyer data to evolve a recommendation system, to predict their desire, they use buyers background and actions, then it helps E-commerce sites to make appropriate recommendations [7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A novel Based-Approach Composed of Clustering Algorithm & Cosine Similarity for Products Recommendation

Al-Hagery

2020

International Journal of Education and Information Technologies

View full text Add to dashboard Cite

There are huge tons of transactions being accomplished online every day. This implies that ecommerce is facing the problem of data and information overloads. While customers are shopping via websites, they spend a lot of time to search for the required products based on their needs. This problem can easily be alleviated by having an accurate recommendation system based on a strong algorithm and confident measures in this regard. There are two main techniques for products recommendation; content-based filtering and collaborative filtering. If one of these two techniques implemented on the e-commerce system, a lot of limitations and weak points will appear. This paper aims at generating an optimal list of product, which, in turn, generates an accurate and reliable list of items. The new approach is composed of three components; clustering algorithm, user-based collaborative filtering, and the Cosine similarity measure. This approach implemented using a real dataset of past experienced users. The accuracy of the search results is a matter to users, it recommends the most appropriate products to users of the e-commerce website. This approach shows trustworthy results and achieved a high level of accuracy for recommending products to users.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A novel Based-Approach Composed of Clustering Algorithm & Cosine Similarity for Products Recommendation

Al-Hagery

2020

International Journal of Education and Information Technologies

View full text Add to dashboard Cite

show abstract

“…Multi-criteria ratings RS aims at leveraging historical ratings with users" and items" additional information such as reviews and contextual features to predict user preferences for a personalized recommendation. For review-based recommendations, most existing approaches make a prediction on unknown ratings by implementing the sentiment/polarity on reviews as a whole such as [13]- [15]. Furthermore, most existing approaches in multi-criteria RS are focusing on utilizing contextual information which available explicitly (e.g.…”

Section: Introductionmentioning

confidence: 99%

Tensorized Neural Network for Multi-Aspect Rating-Based Recommendation

2019

IJRTE

View full text Add to dashboard Cite

Generating personalized recommendations is one of the most crucial aspects in Recommender System research area. Most of the researches only focus on the accuracy of recommendation using collaborative filtering that relies on a single overall rating that represents the overall preferences. However, the user may have a different emphasis on different specific aspects that affect the users’ final rating decisions. Therefore, we present a neural network model that utilize multi-aspects ratings using Tensor Factorization to improve the accuracy of personalization, as well as optimizing the dynamic weights of the aspect. To measure the estimated weights for the aspects, we employ the Higher Order Singular Value Decomposition (HOSVD) technique called CANDECOMP/PARAFAC (CP) decomposition that allows for multi-faceted data processing. We then develop the Neural Network with backpropagation error to train the model with different parameter settings and limited computational time. We also use a non-linear activation function in each hidden layer in various settings. The experimental result measured using MAE shows that the proposed model has significantly outperformed the baseline approach in terms of the prediction accuracy. Based on the observation, the performance of rating prediction has been improved by employing the Tensorized Neural Network model and can overcome the problem of local optimum convergence for multi-aspect rating recommendation.

show abstract

“…how well a customer's preference on a product is predicted by the system. Accuracy is no doubt of great importance in evaluating the recommendation effectiveness, which can be exemplified by a large pool of studies dedicated to improve the accuracy of recommendation methods [3][4][5][6][7]. Recently, recommendation diversity has been recognized as another important aspect for increasing customers' satisfaction and the sales of electronic commerce [8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

An adjustable re-ranking approach for improving the individual and aggregate diversities of product recommendations

Wang¹,

Yu²,

Deng³

2018

Electron Commer Res

View full text Add to dashboard Cite

The effectiveness of product recommendations is previously assessed based on recommendation accuracy. Recently, individual diversity and aggregate diversity of product recommendations have been recognized as important dimensions in evaluating the recommendation effectiveness. However, the gain of either diversity is usually at the cost of accuracy and the increase of one diversity does not guarantee a significant improvement in the other. A few attempts have been made to achieve reasonable trade-offs either between recommendation accuracy and individual diversity or between recommendation accuracy and aggregate diversity. Little attention has been paid to obtain a balance among the three important aspects of product recommendations. To address this problem, we propose an adjustable re-ranking approach that incorporates two new ranking criteria for improving both diversities. Three ranking lists are generated to guarantee recommendation accuracy, individual diversity, and aggregate diversity, respectively. The three ranking lists are finally merged with tunable parameters to generate a recommendation list. To evaluate the proposed method, experiments are conducted on a data set obtained from Alibaba. The results show that the proposed method achieves much higher improvements in both diversities than the baseline methods when sacrificing the same amount of recommendation accuracy.

show abstract

Personalized recommendation based on customer preference mining and sentiment assessment from a Chinese e-commerce website

Cited by 33 publications

References 32 publications

A novel Based-Approach Composed of Clustering Algorithm & Cosine Similarity for Products Recommendation

A novel Based-Approach Composed of Clustering Algorithm & Cosine Similarity for Products Recommendation

Tensorized Neural Network for Multi-Aspect Rating-Based Recommendation

An adjustable re-ranking approach for improving the individual and aggregate diversities of product recommendations

Contact Info

Product

Resources

About