Understanding and combating link farming in the twitter social network

@article{Ghosh2012UnderstandingAC,
  title={Understanding and combating link farming in the twitter social network},
  author={Saptarshi Ghosh and Bimal Viswanath and Farshad Kooti and Naveen Kumar Sharma and Gautam Korlam and Fabr{\'i}cio Benevenuto and Niloy Ganguly and Krishna P. Gummadi},
  journal={Proceedings of the 21st international conference on World Wide Web},
  year={2012}
}
Recently, Twitter has emerged as a popular platform for discovering real-time information on the Web, such as news stories and people's reaction to them. [] Key Result Our findings shed light on the social dynamics that are at the root of the link farming problem in Twitter network and they have important implications for future designs of link spam defenses.

Figures and Tables from this paper

An empirical study of socialbot infiltration strategies in the Twitter social network

TLDR
An analysis of 120 socialbot accounts in Twitter, which have a profile, follow other users, and generate tweets either by reposting others’ tweets or by generating their own synthetic tweets, reveals what strategies make socialbots successful in the Twitter sphere.

Network Analysis of Recurring Twitter Spam Campaign

  • Akhil A. Dixit
  • Computer Science
    International Journal for Research in Applied Science and Engineering Technology
  • 2019
TLDR
The deceptive information is one of the key factors to the spreading efficiency of spam on Twitter, and a better understanding of deceiving information is crucial to spam detection techniques.

ENWalk: Learning Network Features for Spam Detection in Twitter

TLDR
ENWalk is proposed, a framework to detect the spammers by learning the feature representations of the users in the social media using the random walks biased on the spam dynamics and the results discover novel dynamics of spamming which are intuitive and arguable.

A survey on Analyzing and Measuring Trustworthiness of User-Generated Content on Twitter during High-Impact Events

TLDR
A literature survey of the various research work done around the domain of analyzing and measuring trustworthiness of user-generated content on Twitter to study high-impact events is presented.

A community role approach to assess social capitalists visibility in the Twitter network

TLDR
This work applies a recently proposed method allowing to identify social capitalists to the case of social capitalists and shows they are highly visible on Twitter, due to the specific roles they hold.

Understanding Factors That Affect Web Traffic via Twitter

TLDR
This paper introduces the Multi-Task Learning MTL to build a model for predicting the number of clicks, which takes into account the specific characters of users with different influence levels to improve the predictive accuracy.

Social capitalists on Twitter: detection, evolution and behavioral analysis

TLDR
This work provides a method to detect social capitalists, a special kind of users in Twitter that act like automatic accounts, and shows that these users form a highly connected group in the network by studying their neighborhoods and their local clustering coefficient.

On the importance of considering social capitalism when measuring influence on Twitter

TLDR
This work defines a classifier that discriminates social capitalists from real, truthful users and uses it to balance Klout's score to adjust influential scores, and developed an application that allows using the classifier online.

Twitter games: how successful spammers pick targets

TLDR
Investigation of the strategies Twitter spammers employ to reach relevant target audiences finds evidence of a large number of the spam accounts forming relationships with other Twitter users, thereby becoming deeply embedded in the social network.

Reverse engineering socialbot infiltration strategies in Twitter

TLDR
This analysis is the first of a kind, and reveals what strategies make socialbots successful in the Twitter-sphere, and employs a 2k factorial design experiment to quantify the infiltration effectiveness of different socialbot strategies.
...

References

SHOWING 1-10 OF 36 REFERENCES

TwitterRank: finding topic-sensitive influential twitterers

TLDR
Experimental results show that TwitterRank outperforms the one Twitter currently uses and other related algorithms, including the original PageRank and Topic-sensitive PageRank, which is proposed to measure the influence of users in Twitter.

#TwitterSearch: a comparison of microblog search and web search

TLDR
This paper explores search behavior on the popular microblogging/social networking site Twitter and observes that people search Twitter to find temporally relevant information and information related to people, and the results returned from the different corpora support these different uses.

Detecting Spammers on Twitter

TLDR
This paper uses tweets related to three famous trending topics from 2009 to construct a large labeled collection of users, manually classified into spammers and non-spammers, and identifies a number of characteristics related to tweet content and user social behavior which could potentially be used to detect spammers.

Measuring User Influence in Twitter: The Million Follower Fallacy

TLDR
An in-depth comparison of three measures of influence, using a large amount of data collected from Twitter, is presented, suggesting that topological measures such as indegree alone reveals very little about the influence of a user.

Suspended accounts in retrospect: an analysis of twitter spam

TLDR
This study examines the abuse of online social networks at the hands of spammers through the lens of the tools, techniques, and support infrastructure they rely upon and identifies an emerging marketplace of illegitimate programs operated by spammers.

Seven Months with the Devils: A Long-Term Study of Content Polluters on Twitter

TLDR
This paper presents the first long-term study of social honeypots for tempting, profiling, and filtering content polluters in social media, and evaluates a wide range of features to investigate the effectiveness of automatic content polluter identification.

Uncovering social spammers: social honeypots + machine learning

TLDR
It is found that the deployed social honeypots identify social spammers with low false positive rates and that the harvested spam data contains signals that are strongly correlated with observable profile features (e.g., content, friend information, posting patterns, etc.).

Overcoming Spammers in Twitter – A Tale of Five Algorithms1

TLDR
The vulnerability of five different algorithms to linking malpractice in Twitter is examined and a first step towards “desensitizing” them against such abusive behavior is proposed.

Fragile online relationship: a first look at unfollow dynamics in twitter

TLDR
This work collects daily snapshots of the online relationships of 1.2 million Korean-speaking users for 51 days as well as all of their tweets to discover the major factors, including the reciprocity of the relationships, the duration of a relationship, the followees' informativeness, and the overlap of the relationship, which affect the decision to unfollow.

@spam: the underground on 140 characters or less

TLDR
A characterization of spam on Twitter finds that 8% of 25 million URLs posted to the site point to phishing, malware, and scams listed on popular blacklists, and examines whether the use of URL blacklists would help to significantly stem the spread of Twitter spam.