Detection of malicious social bots: A survey and a refined taxonomy

Latah, Majd

doi:10.1016/j.eswa.2020.113383

Cited by 57 publications

(39 citation statements)

References 122 publications

(216 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It was also shown that machine learning methods and, more specifically, random forest classifiers are the most commonly used for detecting social bots in Twitter users. Majd Latah [16] presented a comprehensive review focusing on malicious social bots' stealthy manner and their detection techniques. The author precisely reviewed detection approaches, which are graphbased, machine learning based, and emerging approaches.…”

Section: Related Surveysmentioning

confidence: 99%

“…For example, verified accounts are guaranteed to be human users. Moreover, the ratio of followers to following and the age of the account are considered discriminative characteristics in detecting bots since bots generally mass-follow and have short life span [16]. The following features are mainly used by tweetbased bot detection techniques to distinguish between tweetbased bots and humans accounts [23]:…”

Section: Tweet-based Bot Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Tweet-Based Bot Detection Using Big Data Analytics

et al. 2021

View full text Add to dashboard Cite

Section: Related Surveysmentioning

confidence: 99%

Section: Tweet-based Bot Detectionmentioning

confidence: 99%

Tweet-Based Bot Detection Using Big Data Analytics

et al. 2021

View full text Add to dashboard Cite

“…Undeutsch Hypothesis [234] Factual contents differ in quality and style from fallacy Source (User) Related Theories Expertise Community/ Peer Influence Rare Behavior [18] Unusual behavior than majority Expertise: [235], [236] Synchronized Behavior [18] All such user show/ follow the similar behavior patterns.…”

Section: Completely Distinct Considerations Recommended (Not Included In Any Research Category)mentioning

confidence: 99%

“…It becomes more challenging when source/user authenticity is hidden from the viewer, though user anonymity is one of the prose of microblogs. Unfortunately, it also welcome some other issues like: user's coordinated behavior [18], follower's fallacy [19], etc. It not only affects the quality of microblogs content but also introduces another challenge for gauging the source credibility.…”

Section: Introductionmentioning

confidence: 99%

Social Media and Microblogs Credibility: Identification, Theory Driven Framework, and Recommendation

2021

View full text Add to dashboard Cite

Social media microblogs are extensively used to get news and other information. It brings the real challenge to distinguish that what particular information is credible. Especially when user authenticity is hidden, due to the microblog's anonymity feature. Low credibility content creates an imbalance in society. Therefore many research studies are conducted to assess automatic microblog's credibility but the majority of them offer different concepts of credibility and the problem seems unresolved. Credibility is multidisciplinary, hence there is no generalized or accepted credibility concept with all its necessary and detailed constructs/components. Therefore, it is necessary to understand the complete anatomy of information credibility from different disciplines. It is accomplished here through an in-depth and organized study of all the problem dimensions for the identification of comprehensive and necessary credibility constructs. The framework is also proposed based on the identified constructs. It adheres to these constructs and presents their inter-relationships. It is believed that the framework would provide the necessary building blocks for implementing an effective automatic credibility assessment system. The framework is generic to social media and specifically implemented for microblogs. It is completely transformed up to features level, in the context of microblogs. Regarding automatic credibility assessment, it is proposed after detailed analysis that the attempt should be made for hybrid models combining feature-based and graph-based approaches. It is observed that quite a few surveys in the literature focus on some limited aspects of microblogs credibility but no literature survey and fundamental study exists that consolidates the work done. To understand the broader domain of credibility and consolidate the work in this area that can lead us to a suitable framework, we explored the existing literature from different disciplines for the said objectives. We categorized them along various dimensions, developed taxonomy, identified gaps and challenges, proposed a solution, developed a theory-driven framework with its transformation to microblogs, and suggested key areas of research.

show abstract

“…People may write this type of fake reviews to promote their products or to defame their competitors' products. • Bot detection [82]. Social media is now populated by small programs designed to exhibit human-like behavior called social bots [83] that automatically spread posts to give the impression that a given piece of information is highly popular and endorsed by many people.…”

mentioning

confidence: 99%

Sentiment Analysis for Fake News Detection

et al. 2021

View full text Add to dashboard Cite

In recent years, we have witnessed a rise in fake news, i.e., provably false pieces of information created with the intention of deception. The dissemination of this type of news poses a serious threat to cohesion and social well-being, since it fosters political polarization and the distrust of people with respect to their leaders. The huge amount of news that is disseminated through social media makes manual verification unfeasible, which has promoted the design and implementation of automatic systems for fake news detection. The creators of fake news use various stylistic tricks to promote the success of their creations, with one of them being to excite the sentiments of the recipients. This has led to sentiment analysis, the part of text analytics in charge of determining the polarity and strength of sentiments expressed in a text, to be used in fake news detection approaches, either as a basis of the system or as a complementary element. In this article, we study the different uses of sentiment analysis in the detection of fake news, with a discussion of the most relevant elements and shortcomings, and the requirements that should be met in the near future, such as multilingualism, explainability, mitigation of biases, or treatment of multimedia elements.

show abstract

Detection of malicious social bots: A survey and a refined taxonomy

Cited by 57 publications

References 122 publications

Tweet-Based Bot Detection Using Big Data Analytics

Tweet-Based Bot Detection Using Big Data Analytics

Social Media and Microblogs Credibility: Identification, Theory Driven Framework, and Recommendation

Sentiment Analysis for Fake News Detection

Contact Info

Product

Resources

About