An analysis of user influence ranking algorithms on Dark Web forums

Yang, Christopher C.; Tang, Xuning; Thuraisingham, Bhavani

doi:10.1145/1938606.1938616

Cited by 29 publications

(15 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some used SNA metrics and algorithms, such as centrality measures and Page Rank algorithm [22], while others used text mining techniques [23]. However, few studies tried to combine several techniques to identify key and influential members in suspicious groups [24]. In our study, we adopt a hybrid approach as we utilise several SNA metrics to identify key players in the group, then we perform text sentiment analysis and temporal analysis to gain further insights.…”

Section: Background and Related Workmentioning

confidence: 99%

Identifying Key-Players in Online Activist Groups on the Facebook Social Network

Nouh

Nurse

2015

2015 IEEE International Conference on Data Mining Workshop (ICDMW)

View full text Add to dashboard Cite

Online social media applications have become an integral part of our everyday life. Not only are they being utilised by individuals and legitimate businesses, but also recently several organised groups, such as activists, hactivists, and cyber-criminals have adopted them to communicate and spread their ideas. This represents a new source for intelligence gathering for law enforcement for instance, as it allows them an inside look at the behaviour of these previously closed, secretive groups. One possible opportunity with this online data source is to utilise the public exchange of social-media messages to identify key users in such groups. This is particularly important for law enforcement that wants to monitor or interrogate influential people in suspicious groups. In this paper, we utilise Social Network Analysis (SNA) techniques to understand the dynamics of the interaction between users in a Facebookbased activist group. Additionally, we aim to identify the most influential users in the group and infer their relationship strength. We incorporate sentiment analysis to identify users with clear positive and negative influences on the group; this could aid in facilitating a better understanding of the group. We also perform a temporal analysis to correlate online activities with relevant real-life events. Our results show that applying such data analysis techniques on users online behaviour is a powerful tool to predict levels of influence and relationship strength between group members. Finally, we validated our results against the ground truth and found that our approach is very promising at achieving its aims.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Identifying Key-Players in Online Activist Groups on the Facebook Social Network

Nouh

Nurse

2015

2015 IEEE International Conference on Data Mining Workshop (ICDMW)

View full text Add to dashboard Cite

show abstract

“…Expert search and ranking problem has become an active research area in various application domains. However, it was studied in different contexts including the TREC enterprise track [9], question answering (QA) Websites [10], [5], [11], enterprises such as email communication [12], and scientific networks in digital libraries [13], [14].…”

Section: Related Workmentioning

confidence: 99%

“…They find that various network structures affect the performance of these algorithms. Yang et al [11] investigate the user influences ranking on dark web forums. Besides to link analysis, they consider features that reflect user influence in particular, message content similarity and response immediacy and developed UserRank algorithm.…”

Section: Related Workmentioning

confidence: 99%

Robust Expert Ranking in Online Communities - Fighting Sybil Attacks

Rashed

Balasoiu

Klamma

2012

Proceedings of the 8th IEEE International Conference on Collaborative Computing: Networking, Applications and Worksharing

View full text Add to dashboard Cite

Nowadays, many online communities provide means for users to contribute in the evaluation of community created media by tagging, commenting and rating. Judging the users expertise in such collaborative systems is an important issue. As these systems are becoming increasingly popular, they are attackable, e.g. by Sybil Attacks. Thus, an effective expert ranking strategy must be robust to such attacks. In this paper, we propose MHITS, an algorithm to rank users' expertise by exploiting the number of users' fair ratings and direct trust users gain in the online community. We integrate SumUp, a Sybil-resilient algorithm, into MHITS algorithm as a robust ranking strategy. Experimental results show the effectiveness of the proposed method, which can ensure that the highly ranked experts are highly trusted users and provide the high number of fair ratings for the relevant media. We contribute to the experimental evaluation of algorithms for online systems, fighting malicious behavior.

show abstract

“…The content of online interactions has been significantly under explored in trust research. More recently, research in dark web forums combines link analysis with content analysis to model groups and determine influential users [8,10]. However, methods have yet to be explored in analyzing trust relationships.…”

Section: Introductionmentioning

confidence: 99%

Content feature enrichment for analyzing trust relationships in web forums

Piorkowski

Zhou

2013

Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining

View full text Add to dashboard Cite

As criminals and terrorist employ social media platforms for planning and executing nefarious activities, understanding the degree of trustworthiness in interactions among actors becomes crucial for detecting their activities. Measuring trust in these environments can benefit analysts who are monitoring web forums to detect criminal or terrorist activities. Previous research proposed a trust model that could enable automatic trust discovery using speech act theory. This paper introduces a new classification method that enriches traditional techniques with contextual information. We conducted experiments to compare the proposed method with traditional approaches. The results show that the proposed method outperforms other alternative methods.

show abstract

An analysis of user influence ranking algorithms on Dark Web forums

Cited by 29 publications

References 9 publications

Identifying Key-Players in Online Activist Groups on the Facebook Social Network

Identifying Key-Players in Online Activist Groups on the Facebook Social Network

Robust Expert Ranking in Online Communities - Fighting Sybil Attacks

Content feature enrichment for analyzing trust relationships in web forums

Contact Info

Product

Resources

About