Detecting Collusive Spamming Activities in Community Question Answering

Abstract

Community Question Answering (CQA) portals provide rich sources of information on a variety of topics. However, the authenticity and quality of questions and answers (Q&As) has proven hard to control. In a troubling direction, the widespread growth of crowdsourcing websites has created a large-scale, potentially difficult-to-detect workforce to manipulate malicious contents in CQA. The crowd workers who join the same crowdsourcing task about promotion campaigns in CQA collusively manipulate deceptive Q&As for promoting a target (product or service). The collusive spamming group can fully control the sentiment of the target. How to utilize the structure and the attributes for detecting manipulated Q&As? How to detect the collusive group and leverage the group information for the detection task?To shed light on these research questions, we propose a unified framework to tackle the challenge of detecting collusive spamming activities of CQA. First, we interpret the questions and answers in CQA as two independent networks. Second, we detect collusive question groups and answer groups from these two networks respectively by measuring the similarity of the contents posted within a short duration. Third, using attributes (individuallevel and group-level) and correlations (user-based and contentbased), we proposed a combined factor graph model to detect deceptive Q&As simultaneously by combining two independent factor graphs. With a large-scale practical data set, we find that the proposed framework can detect deceptive contents at early stage, and outperforms a number of competitive baselines.

Identifying reputation collectors in community question answering (CQA) sites: Exploring the dark side of social media

“…However, they were silent about identifying such Reputation Collectors automatically. Liu, Liu, Zhou, Zhang, and Ma (2017) proposed a system that detected the collusive spanning activity on CQA sites. They collected data from two different sites namely Zhubajie.com and RapidWorkers.com.…”

Spotting review spammer groups: A cosine pattern and network based method

“…Besides, some researchers proposed network-based spammer detection methods, which model the users, reviews, products, and their relations as a review network and then propagate the spam labels along the edges 19 or compute the suspicious score by an iterative algorithm similar to HITS. 27 However, compared with review spam or spammer detection, limited works have been done for spammer group detection on product review. To further improve the detection accuracy, many efforts also attempt to combine the user behaviors with review network to identify spammers.…”

“…Spammer group detection has received widely attention on the areas of social media, 24,25 shilling attack on recommender systems, 26 and community question answering (CQA). 27 However, compared with review spam or spammer detection, limited works have been done for spammer group detection on product review. 8 Existing works usually use frequent itemset mining (FIM) to discover group candidates first and then identify the candidates as spammer or non-spammer groups using unsupervised ranking methods.…”

Towards Finding Code Snippets on a Question and Answer Website Causing Mobile App Vulnerabilities

“…Liu et al [23] proposed a unified framework to tackle the challenge of detecting collusive spamming activities of Community Question Answering, which provides rich sources of information on a variety of topics. They also proposed a combined factor graph model to detect deceptive Q&As simultaneously by combining two independent factor graphs.…”