4.7 Article

User-based network embedding for opinion spammer detection

Journal

PATTERN RECOGNITION
Volume 125, Issue -, Pages -

Publisher

ELSEVIER SCI LTD
DOI: 10.1016/j.patcog.2021.108512

Keywords

Spam detection; Collective spammer; Network embedding; Signed network

Funding

  1. National Natural Science Foundation of China [L1924068, 61602197, 61772076, 61972448]
  2. CCF-AFSG Research Fund [RF20210005]

Ask authors/readers for more resources

Due to the significant commercial interests, there is a proliferation of spam reviews aimed at manipulating product reputation. In order to effectively detect collective opinion spammers, this paper proposes an unsupervised network embedding-based approach that utilizes different types of user relationships to represent relevance. Experimental results show significant improvements in AP and AUC compared to existing solutions.
Due to the huge commercial interests behind online reviews, a tremendous amount of spammers manufacture spam reviews for product reputation manipulation. To further enhance the influence of spam reviews, spammers often collaboratively post spam reviews within a short period of time, the activities of whom are called collective opinion spam campaign . The goals and members of the spam campaign activities change frequently, and some spammers also imitate normal purchases to conceal the identity, which makes the spammer detection challenging. In this paper, we propose an unsupervised network embedding-based approach to jointly exploiting different types of relations, e.g., direct common behavior relation, and indirect co-reviewed relation to effectively represent the relevances of users for detecting the collective opinion spammers. The average improvements of our method over the state-of-the-art solutions on dataset AmazonCn and YelpHotel are [14.09%,12.04%] and [16.25%,12.78%] in terms of AP and AUC, respectively. (c) 2022 Elsevier Ltd. All rights reserved.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available