Home > Research > Publications & Outputs > Understanding Large-Scale Network Effects in De...

Research

Links

Text available via DOI:

Keywords

View graph of relations

Understanding Large-Scale Network Effects in Detecting Review Spammers

Research output: Contribution to Journal/Magazine › Journal article › peer-review

E-pub ahead of print

Standard

Understanding Large-Scale Network Effects in Detecting Review Spammers. / Rout, Jitendra Kumar; Sahoo, Kshira Sagar; Dalmia, Anmol et al.
In: IEEE Transactions on Computational Social Systems, 14.02.2023.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Rout, JK, Sahoo, KS, Dalmia, A, Bakshi, S, Bilal, M & Song, H 2023, 'Understanding Large-Scale Network Effects in Detecting Review Spammers', IEEE Transactions on Computational Social Systems. https://doi.org/10.1109/TCSS.2023.3243139

APA

Rout, J. K., Sahoo, K. S., Dalmia, A., Bakshi, S., Bilal, M., & Song, H. (2023). Understanding Large-Scale Network Effects in Detecting Review Spammers. IEEE Transactions on Computational Social Systems. Advance online publication. https://doi.org/10.1109/TCSS.2023.3243139

Vancouver

Rout JK, Sahoo KS, Dalmia A, Bakshi S, Bilal M, Song H. Understanding Large-Scale Network Effects in Detecting Review Spammers. IEEE Transactions on Computational Social Systems. 2023 Feb 14. Epub 2023 Feb 14. doi: 10.1109/TCSS.2023.3243139

Author

Rout, Jitendra Kumar ; Sahoo, Kshira Sagar ; Dalmia, Anmol et al. / Understanding Large-Scale Network Effects in Detecting Review Spammers. In: IEEE Transactions on Computational Social Systems. 2023.

Bibtex

@article{fe893ba01da54c2391db76ffab247fc1,
title = "Understanding Large-Scale Network Effects in Detecting Review Spammers",
abstract = "Opinion spam detection is a challenge for online review systems and social forum operators. Opinion spamming costs businesses and people money since it deceives customers as well as automated opinion mining and sentiment analysis systems by bestowing undeserved positive opinions on target firms and/or bestowing fake negative opinions on others. One popular detection approach is to model a review system as a network of users, products, and reviews, for example using review graph models. In this article, we study the effects of network scale on network-based review spammer detection models, specifically on the trust model and the SpammerRank model. We then evaluate both network models using two large publicly available review datasets, namely: the Amazon dataset (containing 6 million reviews by more than 2 million reviewers) and the UCSD dataset (containing over 82 million reviews by 21 million reviewers). It has been observed thatSpammerRank model provides a better scaling time for applications requiring reviewer indicators and in case of trust model distributions are flattening out indicating variance of reviews with respect to spamming. Detailed observations on the scaling effects of these models are reported in the result section.",
keywords = "Analytical models, Behavioral sciences, Feature extraction, Online review spam, opinion spam, review graphs, Scalability, Sentiment analysis, spam detection, unlabeled review, Unsolicited e-mail, Writing",
author = "Rout, {Jitendra Kumar} and Sahoo, {Kshira Sagar} and Anmol Dalmia and Sambit Bakshi and Muhammad Bilal and Houbing Song",
year = "2023",
month = feb,
day = "14",
doi = "10.1109/TCSS.2023.3243139",
language = "English",
journal = "IEEE Transactions on Computational Social Systems",
issn = "2329-924X",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

RIS

TY - JOUR

T1 - Understanding Large-Scale Network Effects in Detecting Review Spammers

AU - Rout, Jitendra Kumar

AU - Sahoo, Kshira Sagar

AU - Dalmia, Anmol

AU - Bakshi, Sambit

AU - Bilal, Muhammad

AU - Song, Houbing

PY - 2023/2/14

Y1 - 2023/2/14

N2 - Opinion spam detection is a challenge for online review systems and social forum operators. Opinion spamming costs businesses and people money since it deceives customers as well as automated opinion mining and sentiment analysis systems by bestowing undeserved positive opinions on target firms and/or bestowing fake negative opinions on others. One popular detection approach is to model a review system as a network of users, products, and reviews, for example using review graph models. In this article, we study the effects of network scale on network-based review spammer detection models, specifically on the trust model and the SpammerRank model. We then evaluate both network models using two large publicly available review datasets, namely: the Amazon dataset (containing 6 million reviews by more than 2 million reviewers) and the UCSD dataset (containing over 82 million reviews by 21 million reviewers). It has been observed thatSpammerRank model provides a better scaling time for applications requiring reviewer indicators and in case of trust model distributions are flattening out indicating variance of reviews with respect to spamming. Detailed observations on the scaling effects of these models are reported in the result section.

AB - Opinion spam detection is a challenge for online review systems and social forum operators. Opinion spamming costs businesses and people money since it deceives customers as well as automated opinion mining and sentiment analysis systems by bestowing undeserved positive opinions on target firms and/or bestowing fake negative opinions on others. One popular detection approach is to model a review system as a network of users, products, and reviews, for example using review graph models. In this article, we study the effects of network scale on network-based review spammer detection models, specifically on the trust model and the SpammerRank model. We then evaluate both network models using two large publicly available review datasets, namely: the Amazon dataset (containing 6 million reviews by more than 2 million reviewers) and the UCSD dataset (containing over 82 million reviews by 21 million reviewers). It has been observed thatSpammerRank model provides a better scaling time for applications requiring reviewer indicators and in case of trust model distributions are flattening out indicating variance of reviews with respect to spamming. Detailed observations on the scaling effects of these models are reported in the result section.

KW - Analytical models

KW - Behavioral sciences

KW - Feature extraction

KW - Online review spam

KW - opinion spam

KW - review graphs

KW - Scalability

KW - Sentiment analysis

KW - spam detection

KW - unlabeled review

KW - Unsolicited e-mail

KW - Writing

U2 - 10.1109/TCSS.2023.3243139

DO - 10.1109/TCSS.2023.3243139

M3 - Journal article

AN - SCOPUS:85149394563

JO - IEEE Transactions on Computational Social Systems

JF - IEEE Transactions on Computational Social Systems

SN - 2329-924X

ER -