Learning to rank products based on online product reviews using a hierarchical deep neural network

Lee, Ho Chang; Rim, Hae Chang; Lee, Do Gil

doi:10.1016/j.elerap.2019.100874

Cited by 32 publications

(20 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These are consistent with the findings of Saumya et al (2018) that the inclusion of new features in the design of review systems can add to the reliability of the data. Further studies into the product ranking model by Lee et al (2019) to employ a multi-task method of learning product rankings and review ratings is vital to creating these new features.…”

Section: Discussionmentioning

confidence: 99%

“…Their experiment showed that inclusion of features from product description data and customer question-answer data improves the prediction accuracy of the helpfulness score. Lee et al (2019) building on the earlier system, added new features in a novel unified learning-approach for ranking products based on online product reviews. This approach enables effective capture of the underlying features of online product reviews in a hierarchical order.…”

Section: Ranking Of Reviewsmentioning

confidence: 99%

“…This approach enables effective capture of the underlying features of online product reviews in a hierarchical order. 'The use of hierarchical networks in product ranking makes it possible to utilize multilevel features and improves the ranking performance' (Lee et al, 2019).…”

Section: Ranking Of Reviewsmentioning

confidence: 99%

“…The extant literature has recently been finding solutions to some notable challenges faced by managers of online reviews namely: (i) usefulness of online reviews (Liu and Park, 2015;Marinkovic and Kalinic, 2017;Sebastianelli and Tamimi, 2018;Zhang and Lin, 2018), (ii) quality and reliability of consumer reviews as against the increasing quantities (Yagci and Das, 2018;Yang and Chao, 2018;Chakraborty, 2019), (iii) review-based ranking of reviews (Chen et al, 2017;Saumya et al, 2018;Lee et al, 2019), (iv) user recommendation (Xu and Yao, 2015;Luan et al, 2018) and (v) the valence or effectiveness of the reviews (Baker and Kim, 2019;Song et al, 2020;Hong et al, 2020). Varied research methodologies have been applied in these studies such as statistical experiments (Kwok and Xie, 2016;Zhang and Lin, 2018), evaluation and categorization of online reviews (Chen, 2016), surveys (Lee et al, 2017;Liu et al, 2018), modeling (Pan et al, 2018) and designed theoretical frameworks (Banerjee and Chua, 2014).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Online Information Review Research and Its Future Direction: A Literature Review

Alimo¹,

Davis²,

Amanor³

2020

theijbm

View full text Add to dashboard Cite

Online reviews offer businesses feedbacks on their products and services toward proper planning and customer satisfaction. Previous studies have helped in improving innovation and giving business solutions on this important aspect of business management, but also identified some challenges. The purpose of this review is to identify research gaps in the extant literature and recommend them for future studies, relevant to online information. This paper conducts a comprehensive literature review of 64 peer-reviewed publications (2008 till date) sampled from selected SCI/SSCI papers on online reviews. The study analyzes the major research problems identified in the literature, identifies the methodologies and theoretical frameworks applied and conducts qualitative content analyses of the findings. The findings reveal the need for more multilingual online review and recommender systems, addition of more consumer review reward-mechanisms and motivations, enhancing interest of netizens in eWOM communications and the need for new features to disallow review modification after submission. It further presents recommendations for future research, relevant to online information review to increase reliability, improve ranking, user reference and usefulness of reviews.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Ranking Of Reviewsmentioning

confidence: 99%

Section: Ranking Of Reviewsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Online Information Review Research and Its Future Direction: A Literature Review

Alimo¹,

Davis²,

Amanor³

2020

theijbm

View full text Add to dashboard Cite

show abstract

“…If there are too many indices, the problem analysis will become very complex and require a huge computing power. In severe cases, the algorithm may face overfitting or fail to find the optimal solution [12,13].…”

Section: Pcamentioning

confidence: 99%

A Hierarchical Model of E-Commerce Sellers Based on Data Mining

Bai¹

2020

ISI

View full text Add to dashboard Cite

This paper attempts to accurately classify e-commerce sellers based on data mining. Firstly, the original data from an e-commerce platform were preprocessed, and the classification indices were identified from five categories (products, users, traffic, sales and basic attribute). Next, the principal component analysis (PCA) and the self-organizing feature map (SOM) were fused into a hierarchical model that divides e-commerce sellers into three categories: large sellers, medium sellers and small sellers. The effectiveness of our model was verified through experiments. Finally, several operating strategies were put forward for e-commerce sellers in each category. The research results provide a good reference for the development of the e-commerce industry.

show abstract

Learning to Rank in Session-Based Recommender Systems

Ravanmehr,

Mohamadrezaei

2023

Session-Based Recommender Systems Using Deep Learning

View full text Add to dashboard Cite

Learning to rank products based on online product reviews using a hierarchical deep neural network

Cited by 32 publications

References 21 publications

Online Information Review Research and Its Future Direction: A Literature Review

Online Information Review Research and Its Future Direction: A Literature Review

A Hierarchical Model of E-Commerce Sellers Based on Data Mining

Learning to Rank in Session-Based Recommender Systems

Contact Info

Product

Resources

About