Identifying unreliable online hospitality reviews with biased user-given ratings: A deep learning forecasting approach

Tianxiang Zheng; Feiran Wu; Rob Law; Qihang Qiu; Rong Wu

doi:10.1016/j.ijhm.2020.102658

Identifying unreliable online hospitality reviews with biased user-given ratings: A deep learning forecasting approach

Tianxiang Zheng
, Feiran Wu
, Rob Law
, Qihang Qiu
, Rong Wu

Research output: Journal article publication › Journal article › Academic research › peer-review

51 Citations (Scopus)

Abstract

This study considers the review reliability problem by identifying biased user-given ratings through rating prediction on the basis of the textual content. Deep learning approaches were introduced to investigate the textual review and validate the effect of rating prediction using a dataset collected from Yelp. The definition of “biased rating” was clarified and influenced the matching rules. The approach obtains high performance on a total of 1,000,000 reviews for prediction, with user-given ratings as the benchmark. Using the revealed biased ratings, unreliable reviews were detected by combining the results of several deep learning kernels. Findings shed light on understanding review quality by distinguishing biased ratings and unreliable reviews that may cause inconsistency and ambiguity to readers. Hence, theoretical and managerial areas for social media analytics are enriched on the basis of online review meta-data in hospitality and tourism.

Original language	English
Article number	102658
Journal	International Journal of Hospitality Management
Volume	92
DOIs	https://doi.org/10.1016/j.ijhm.2020.102658
Publication status	Published - Jan 2021

Keywords

Deep learning
Information quality
Online customer review
Review rating prediction
Review reliability

ASJC Scopus subject areas

Tourism, Leisure and Hospitality Management
Strategy and Management

More information

10.1016/j.ijhm.2020.102658

Cite this

@article{d86a494687a649c487b526a7ba8ab48c,

title = "Identifying unreliable online hospitality reviews with biased user-given ratings: A deep learning forecasting approach",

abstract = "This study considers the review reliability problem by identifying biased user-given ratings through rating prediction on the basis of the textual content. Deep learning approaches were introduced to investigate the textual review and validate the effect of rating prediction using a dataset collected from Yelp. The definition of “biased rating” was clarified and influenced the matching rules. The approach obtains high performance on a total of 1,000,000 reviews for prediction, with user-given ratings as the benchmark. Using the revealed biased ratings, unreliable reviews were detected by combining the results of several deep learning kernels. Findings shed light on understanding review quality by distinguishing biased ratings and unreliable reviews that may cause inconsistency and ambiguity to readers. Hence, theoretical and managerial areas for social media analytics are enriched on the basis of online review meta-data in hospitality and tourism.",

keywords = "Deep learning, Information quality, Online customer review, Review rating prediction, Review reliability",

author = "Tianxiang Zheng and Feiran Wu and Rob Law and Qihang Qiu and Rong Wu",

note = "Funding Information: The authors express their sincere appreciations to Weimin Zheng of the School of Management, Xiamen University, for his helpful discussions and valuable suggestions, to Weiheng (Vincent) Liang of Linxoon (Guangzhou) Information Technology \& Service Co. Ltd, for his technical assistance, and to Rui Li of the Department of Geography and Planning, SUNY at Albany, for his encouragement and critical comments without which this research could not have proceeded to its present form. This work was partially supported by the Special Funds of High-level University Construction Program of Guangdong Province under Grant No. 88018052. Funding Information: This work was partially supported by the Special Funds of High-level University Construction Program of Guangdong Province under Grant No. 88018052 . Publisher Copyright: {\textcopyright} 2020 Elsevier Ltd",

year = "2021",

month = jan,

doi = "10.1016/j.ijhm.2020.102658",

language = "English",

volume = "92",

journal = "International Journal of Hospitality Management",

issn = "0278-4319",

publisher = "Elsevier Ltd",

}

TY - JOUR

T1 - Identifying unreliable online hospitality reviews with biased user-given ratings: A deep learning forecasting approach

AU - Zheng, Tianxiang

AU - Wu, Feiran

AU - Law, Rob

AU - Qiu, Qihang

AU - Wu, Rong

N1 - Funding Information: The authors express their sincere appreciations to Weimin Zheng of the School of Management, Xiamen University, for his helpful discussions and valuable suggestions, to Weiheng (Vincent) Liang of Linxoon (Guangzhou) Information Technology & Service Co. Ltd, for his technical assistance, and to Rui Li of the Department of Geography and Planning, SUNY at Albany, for his encouragement and critical comments without which this research could not have proceeded to its present form. This work was partially supported by the Special Funds of High-level University Construction Program of Guangdong Province under Grant No. 88018052. Funding Information: This work was partially supported by the Special Funds of High-level University Construction Program of Guangdong Province under Grant No. 88018052 . Publisher Copyright: © 2020 Elsevier Ltd

PY - 2021/1

Y1 - 2021/1

N2 - This study considers the review reliability problem by identifying biased user-given ratings through rating prediction on the basis of the textual content. Deep learning approaches were introduced to investigate the textual review and validate the effect of rating prediction using a dataset collected from Yelp. The definition of “biased rating” was clarified and influenced the matching rules. The approach obtains high performance on a total of 1,000,000 reviews for prediction, with user-given ratings as the benchmark. Using the revealed biased ratings, unreliable reviews were detected by combining the results of several deep learning kernels. Findings shed light on understanding review quality by distinguishing biased ratings and unreliable reviews that may cause inconsistency and ambiguity to readers. Hence, theoretical and managerial areas for social media analytics are enriched on the basis of online review meta-data in hospitality and tourism.

AB - This study considers the review reliability problem by identifying biased user-given ratings through rating prediction on the basis of the textual content. Deep learning approaches were introduced to investigate the textual review and validate the effect of rating prediction using a dataset collected from Yelp. The definition of “biased rating” was clarified and influenced the matching rules. The approach obtains high performance on a total of 1,000,000 reviews for prediction, with user-given ratings as the benchmark. Using the revealed biased ratings, unreliable reviews were detected by combining the results of several deep learning kernels. Findings shed light on understanding review quality by distinguishing biased ratings and unreliable reviews that may cause inconsistency and ambiguity to readers. Hence, theoretical and managerial areas for social media analytics are enriched on the basis of online review meta-data in hospitality and tourism.

KW - Deep learning

KW - Information quality

KW - Online customer review

KW - Review rating prediction

KW - Review reliability

UR - https://www.scopus.com/pages/publications/85092407562

U2 - 10.1016/j.ijhm.2020.102658

DO - 10.1016/j.ijhm.2020.102658

M3 - Journal article

AN - SCOPUS:85092407562

SN - 0278-4319

VL - 92

JO - International Journal of Hospitality Management

JF - International Journal of Hospitality Management

M1 - 102658

ER -

Identifying unreliable online hospitality reviews with biased user-given ratings: A deep learning forecasting approach

Abstract

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this