The DOI matches its Crossref record; 57 of the 71 references it cites were found in a registry or an index.
Online Human-Bot Interactions: Detection, Estimation, and Characterization
Open accessAbstract
Increasing evidence suggests that a growing amount of social media content is generated by autonomous entities known as social bots. In this work we present a framework to detect such entities on Twitter. We leverage more than a thousand features extracted from public data and meta-data about users: friends, tweet content and sentiment, network patterns, and activity time series. We benchmark the classification framework by using a publicly available dataset of Twitter bots. This training data is enriched by a manually annotated collection of active Twitter users that include both humans and bots of varying sophistication. Our models yield high accuracy and agreement with each other and can detect bots of different nature. Our estimates suggest that between 9% and 15% of active Twitter accounts are bots. Characterizing ties among accounts, we observe that simple bots tend to interact with bots that exhibit more human-like behaviors. Analysis of content flows reveals retweet and mention strategies adopted by bots to interact with different target groups. Using clustering analysis, we characterize several subclasses of accounts, including spammers, self promoters, and accounts that post content from connected applications.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“A decade of research on social bot detection 13-15 has established that automated accounts exhibit distinctive temporal, linguistic, and network signatures 14,31 .”
From The Moltbook Illusion: Separating Human Influence from Emergent Behavior in AI Agent Societies (2026) · cites this paper as [14]
In the citing paper
“Various characteristics, ranging from account metadata to social network structure, are then considered during the process (Ferrara et al., 2016;Varol et al., 2017).”
From Anatomy of an AI-powered malicious social botnet (2024) · cites this paper as Varol et al., 2017
In the citing paper
“These features are shown to be effective in identifying social bots and are described in detail in the literature [42, 43, 48].”
From Detection of Novel Social Bots by Ensembles of Specialized Classifiers (2020) · cites this paper as [43]
Citations
Cites
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016 · cited 1×
“We benchmarked our system using several off-the-shelf algorithms provided in the scikit-learn library (Pedregosa et al. 2011).”
Method(2008) · Journal of Machine Learning Research · Cited by 33,051
Twitter mood predicts the stock market
Bollen, J., Mao, H., & Zeng, X. (2011) · Journal of Computational Science · doi:10.1016/j.jocs.2010.12.007 · Cited by 5,206 · cited 1×
“Sentiment extracted from social media conversations has been used to forecast offline events including financial market fluctuations (Bollen, Mao, and Zeng 2011), and is known to affect information spreading (Mitchell et al. 2013; Ferrara and Yang 2015).”
Recognizing contextual polarity in phrase-level sentiment analysis
Wilson, T., Wiebe, J., & Hoffmann, P. (2005) · doi:10.3115/1220575.1220619 · Cited by 3,388 · cited 1×
“…extraction techniques to generate various sentiment features, including arousal , valence and dominance scores (Warriner, Kuperman, and Brysbaert 2013), happiness score (Kloumann et al. 2012), polarization and strength (Wilson, Wiebe, and Hoffmann 2005), and emoti-con score (Agarwal et al. 2011).”
Ferrara, E., Varol, O., Davis, C., Menczer, F., & Flammini, A. (2016) · Communications of the ACM · doi:10.1145/2818717 · Cited by 1,973
Self-citationNorms of valence, arousal, and dominance for 13,915 English lemmas
Warriner, A. B., Kuperman, V., & Brysbaert, M. (2013) · Behavior Research Methods · doi:10.3758/s13428-012-0314-x · Cited by 1,959
Sentiment Analysis of Twitter Data
Agarwal, A., Xie, B., Vovsha, I., Rambow, O., & Passonneau, R. J. (2011) · Cited by 1,565
Social bots distort the 2016 U.S. Presidential election online discussion
Bessi, A., & Ferrara, E. (2016) · First Monday · doi:10.5210/fm.v21i11.7090 · Cited by 993 · cited 7×
“Features extracted from user meta-data have been used to classify users and patterns before (Mislove et al. 2011; Ferrara et al. 2016a).”
InfluentialSelf-citationBotOrNot: A System to Evaluate Social Bots
Davis, C. A., Varol, O., Ferrara, E., Flammini, A., & Menczer, F. (2016) · Proceedings of the 25th International Conference Companion on World Wide Web - WWW 16 Companion · doi:10.1145/2872518.2889302 · Cited by 909 · cited 2×
“This system leverages more than one thousand features to evaluate the extent to which a Twitter account exhibits similarity to the known characteristics of social bots (Davis et al. 2016).”
BackgroundMethodSelf-citationIs the Sample Good Enough? Comparing Data from Twitter's Streaming API with Twitter's Firehose
Morstatter, F., Pfeffer, J., Liu, H., & Carley, K. (2021) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v7i1.14401 · Cited by 863 · cited 9×
“For each of these accounts, we collected their tweets through the Twitter Search API.”
MethodInfluential
Cited by
Sorted by citations
Items 201–300 of 933
Leveraging Data-Driven Insights to Enhance Market Share in the Media Industry
Mehra, A. (2023) · Journal for Research in Applied Sciences and Biotechnology · doi:10.55544/jrasb.2.3.37 · Cited by 28
Bot Electioneering Volume: Visualizing Social Bot Activity During Elections
Yang, K.-C., Hui, P.-M., & Menczer, F. (2019) · International World Wide Web Conference (WWW) · doi:10.1145/3308560.3316499 · Cited by 29
“By incorporating the bot-detection ability of Botometer [3, 12, 13], BEV is able to distinguish between content generated by likely bots and humans.”
BackgroundInfluentialSelf-citationBot Detection on Online Social Networks Using Deep Forest
Daouadi, K. E., Rebaï, R. Z., & Amous, I. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-19810-7_30 · Cited by 28
You talkin’ to me? Exploring Human/Bot Communication Patterns during Riot Events
Kušen, E., & Strembeck, M. (2019) · Information Processing & Management · doi:10.1016/j.ipm.2019.102126 · Cited by 29
Drott, E. (2020) · American Music · doi:10.5406/americanmusic.38.2.0153 · Cited by 28
The Impact of Social Endorsement Cues and Manipulability Concerns on Perceptions of News Credibility
Lee, S. S., Liang, F., Hahn, L. B., Lane, D. S., Weeks, B. E., & Kwak, N. (2021) · Cyberpsychology Behavior and Social Networking · doi:10.1089/cyber.2020.0566 · Cited by 32
“7,8 Despite widespread societal concerns over social media manipulation, 9 little is known about how individuals’ concerns over the manipulability of SEC affect how they evaluate news shared on social media.”
Choi, J., & Jeon, C. (2021) · IEEE Access · doi:10.1109/access.2021.3098799 · Cited by 28
“It has been found that one out of every 21 tweets on Twitter can be categorized as spam, and autobots account for approximately 15% of Twitter users [7].”
BackgroundVASSL: A Visual Analytics Toolkit for Social Spambot Labeling
Khayat, M., Karimzadeh, M., Zhao, J. L., & Ebert, D. S. (2019) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2019.2934266 · Cited by 27
Characterizing Social Bots Spreading Financial Disinformation
Tardelli, S., Avvenuti, M., Tesconi, M., & Cresci, S. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-49570-1_26 · Cited by 29
Uncovering Coordinated Networks on Social Media.
Pacheco, D. F., Hui, P.-M., Torres-Lugo, C., Truong, B. T., Flammini, A., & Menczer, F. (2020) · Cited by 33
Self-citationOn Twitter Purge: A Retrospective Analysis of Suspended Users
Chowdhury, F. A., Allen, L., Yousuf, M., & Mueen, A. (2020) · International World Wide Web Conference (WWW) · doi:10.1145/3366424.3383298 · Cited by 30
“Misinformation, spamming, and bot detection are some of the most studied aspects regarding Twitter suspension [15, 18, 22, 30, 33].”
BackgroundThe language and targets of online trolling: A psycholinguistic approach for social cybersecurity
Uyheng, J., Moffitt, J. D., & Carley, K. M. (2022) · Information Processing & Management · doi:10.1016/j.ipm.2022.103012 · Cited by 32
Twitter spam and false accounts prevalence, detection, and characterization: A survey
Ferrara, E. (2022) · First Monday · doi:10.5210/fm.v27i12.12872 · Cited by 34
“● “Botometer considers over 1,000 features that can be categorized into six classes: user profile, friends, network, temporal, content and language, and sentiment [Varol et al., 2017].”
BackgroundSelf-citationProactive Discovery of Fake News Domains from Real-Time Social Media Feeds
Chen, Z., & Freire, J. (2020) · The Web Conference · doi:10.1145/3366424.3385772 · Cited by 31
“This metric uses Bayes’ theorem to “take into account an estimate of the overall prevalence of bots, so as to balance false positives with false negatives [23].”
MethodInfluentialBenchmarking Crisis in Social Media Analytics: A Solution for the Data-Sharing Problem
Assenmacher, D., Weber, D., Preuß, M., Valdez, A. S. C., Bradshaw, A., Roß, B., Cresci, S., Trautmann, H., Neumann, F., & Grimme, C. (2021) · Social Science Computer Review · doi:10.1177/08944393211012268 · Cited by 27
“…relevance of these methods simultaneously and has led to an enormous body of research literature (Bastos & Mercea, 2019; Cresci et al., 2019; Ferrara, 2017; Grimme, Assenmacher, et al., 2017; Hagen et al., 2020; Kollanyi et al., 2016; Neudert, 2017; Nizzoli et al., 2021; Shao et al., 2018;…”
MethodToward a new approach to author profiling based on the extraction of statistical features
Ouni, S., Fkih, F., & Omri, M. N. (2021) · Social Network Analysis and Mining · doi:10.1007/s13278-021-00768-6 · Cited by 26
“Random forest was the classification technique that has been proven to give the best performance for bot detection on Twitter (Lee et al. 2011; Varol et al. 2017; Singh et al. 2018).”
BackgroundMethodT-Bot: AI-based social media bot detection model for trend-centric twitter network
Gera, S., & Sinha, A. (2022) · Social Network Analysis and Mining · doi:10.1007/s13278-022-00897-6 · Cited by 25
“The rapid rise in the number of users participating in OSN conversations has inclined the researchers towards detecting social media bots (Cresci et al. (2017), Perna and Tagarelli (2018), Varol et al. (2017), Morstatter et al. (2016), Zhang and Gupta (2018b)).”
BackgroundSpence, P. R., Edwards, A. P., Edwards, C. C., & Jin, X. (2018) · Behaviour and Information Technology · doi:10.1080/0144929x.2018.1514425 · Cited by 27
“%) may be bots (Varol et al. 2017).”
BackgroundFurman, I., & Tunç, A. (2019) · Policy & Internet · doi:10.1002/poi3.218 · Cited by 30
Klein, A. Z., Cai, H., Weissenbacher, D., Levine, L. D., & Gonzalez‐Hernandez, G. (2020) · Journal of Biomedical Informatics · doi:10.1016/j.yjbinx.2020.100076 · Cited by 25
“A user-level bot detection approach [27] also would be limited because tweets containing reported speech are not necessarily computer-generated.”
BackgroundMapping dynamic human sentiments of heat exposure with location-based social media data
Lyu, F., Zhou, L., Park, J.-W., Baig, F., & Wang, S. (2024) · International Journal of Geographical Information Systems · doi:10.1080/13658816.2024.2343063 · Cited by 32
“It is estimated that up to 15% of Twitter users were automated bot accounts (Varol et al. 2017).”
BackgroundGenerative AI in User-Generated Content
Hua, Y., Niu, S., Cai, J., Chilton, L. B., Heuer, H., & Wohn, D. Y. (2024) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3613905.3636315 · Cited by 30
“For example, a 2016 study unveiled that between 9% and 15% of active Twitter accounts were identified as chatbots [57].”
Fine-Tuned Understanding: Enhancing Social Bot Detection With Transformer-Based Classification
Sallah, A., Alaoui, E. A. A., Agoujil, S., Wani, M. A., Hammad, M. A., Maleh, Y., & El‐Latif, A. A. A. (2024) · IEEE Access · doi:10.1109/access.2024.3440657 · Cited by 28
Theóphilo, A., Pereira, L. A. M., & Rocha, A. D. R. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8683747 · Cited by 25
Twitter User Profiling: Bot and Gender Identification
Kosmajac, D., & Kešelj, V. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58219-7_13 · Cited by 26
Tabloids in the Era of Social Media?
Chakraborty, A., Sarkar, R., Mrigen, A., & Ganguly, N. (2017) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3134665 · Cited by 25
“Similar to organizational accounts, in a recent study, Varol et al. [56] claimed that as much as 15% of Twitter accounts may be bots rather than real people.”
ResultStill out there: Modeling and Identifying Russian Troll Accounts on TwitterPreprint
Im, J., Chandrasekharan, E., Sargent, J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.11162 · Cited by 25
“There are user-based features, friends features, network features, temporal features, content and language features, and sentiment features used to classify each account (Varol et al. 2017).”
MethodToward Mitigating Misinformation and Social Media Manipulation in LLM Era
Zhang, Y., Sharma, K., Du, L., & Liu, Y. (2024) · Companion Proceedings of the ACM Web Conference 2024 · doi:10.1145/3589335.3641256 · Cited by 25
Against Bot Democracy: The Dangers of Epistemic Double-Counting
Tanasoca, A. (2019) · Perspectives on Politics · doi:10.1017/s1537592719001154 · Cited by 24
Bot Datasets on Twitter: Analysis and Challenges
Samper-Escalante, L. D., Loyola‐González, O., Monroy, R., & Medina‐Pérez, M. A. (2021) · Applied Sciences · doi:10.3390/app11094105 · Cited by 26
“The platform estimates that 8.5% of all their active accounts are bots [18], where Varol et al. [19] predict that it is around 15%.”
InfluentialOn the efficacy of old features for the detection of new bots
Nicola, R. D., Petrocchi, M., & Pratelli, M. (2021) · Information Processing & Management · doi:10.1016/j.ipm.2021.102685 · Cited by 24
“The approach has been further investigated by the same authors in [35], where its classification performances are compared with those of Botometer [10].”
InfluentialAuthorship Attribution of Social Media Messages
Theophilo, A., Giot, R., & Rocha, A. (2023) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2021.3123895 · Cited by 25
“For example, according to Varol et al. [9], nearly 15% of Twitter ® accounts (50 million) are automated profiles devised to simulate real people.”
MethodSpam Detection on Arabic Twitter
Mubarak, H., Abdelalí, A., Hassan, S., & Darwish, K. M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60975-7_18 · Cited by 28
Full Cycle Analysis of a Large-Scale Botnet Attack on Twitter
Besel, C., Echeverría, J., & Zhou, S. (2018) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1109/asonam.2018.8508708 · Cited by 25
“[26] states that most normal accounts are in the range of (0.”
BackgroundAlothali, E., Hayawi, K., & Alashwal, H. (2021) · Social Network Analysis and Mining · doi:10.1007/s13278-021-00786-4 · Cited by 25
#CoronaVirus and public health: the role of social media in sharing health information
Kothari, A., Walker, K. K., & Burns, K. S. (2022) · Online Information Review · doi:10.1108/oir-03-2021-0143 · Cited by 28
Alothali, E., Salih, M., Hayawi, K., & Alashwal, H. (2022) · Applied Sciences · doi:10.3390/app12168117 · Cited by 24
Profiling users and bots in Twitter through social media analysis
Pastor-Galindo, J., Mármol, F. G., & Pérez, G. M. (2022) · Information Sciences · doi:10.1016/j.ins.2022.09.046 · Cited by 23
Twitter Bot Detection with Reduced Feature Set
Abreu, J. V. F., Ralha, C. G., & Gondim, J. J. C. (2020) · IEEE International Conference on Intelligence and Security Informatics (ISI) · doi:10.1109/isi49825.2020.9280525 · Cited by 25
“Three different public datasets combined were used ( [22], [23] and [15]) with a set of 140 features.”
BackgroundMethodInfluentialMaking up Audience: Media Bots and the Falsification of the Public Sphere
Santini, R. M., Salles, D., Tucci, G., Ferreira, F., & Grael, F. (2020) · Communication Studies · doi:10.1080/10510974.2020.1735466 · Cited by 22
“Regarding the Bot score of a Twitter account, we used Botometer classi fi er to compute the extent to which an account expresses similarity to the characteristic of a social bot (Varol et al., 2017).”
BackgroundMethodInfluentialRuíz-Núñez, C., Segado-Fernández, S., Jiménez-Gómez, B., Hidalgo, P. J. J., Magdalena, C. S. R., Pollo, M. D. C. Á., García, A. S., & Herrera‐Peco, I. (2022) · Vaccines · doi:10.3390/vaccines10081240 · Cited by 22
Ye, J., & Skiena, S. (2019) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3292500.3330709 · Cited by 20
“It was reported that up to 15 percent of Twitter accounts are in fact bots rather than people [29].”
BackgroundSequeira, R., Gayen, A., Ganguly, N., Dandapat, S. K., & Chandra, J. (2019) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2019.2943238 · Cited by 24
“We subsequently used the Botometer API7 to identify and remove the bot accounts [45].”
BackgroundMethodDeepbot: A Deep Neural Network based approach for Detecting Twitter Bots
Luo, L., Zhang, X., Yang, X., et al. (2020) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/719/1/012063 · Cited by 22
“According to [10], it is estimated that around 48 million registered Twitter users are bots.”
BackgroundA Graph Theory approach to assess nature’s contribution to people at a global scale
de Juan, S., Ospina‐Álvarez, A., Villasante, S., et al. (2021) · Scientific Reports · doi:10.1038/s41598-021-88745-z · Cited by 23
“Brave New World” of Fake News: How It Works
Baptista, J. P., & Gradim, A. (2021) · Javnost - The Public · doi:10.1080/13183222.2021.1861409 · Cited by 29
Tanasoca, A. (2020) · doi:10.1093/oso/9780198851479.001.0001 · Cited by 44
MGTAB: A Multi-Relational Graph-Based Twitter Account Detection Benchmark
Shi, S., Qiao, K., Liu, Z., Yang, J., Chen, C., Chen, J., & Yan, B. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130490 · Cited by 60
AAFA: Associative Affinity Factor Analysis for Bot Detection and Stance Classification in Twitter
Sadiq, S., Yan, Y., Taylor, A. R., et al. (2017) · IEEE International Conference on Information Reuse and Integration (IRI) · doi:10.1109/iri.2017.25 · Cited by 21
“4 million tweets during elections, 1300 tweets per day were produced by bots [11].”
Background(2017) · doi:10.1109/dsaa.2017.57 · Cited by 21
Comparing covariation among vaccine hesitancy and broader beliefs within Twitter and survey data
Nowak, S. A., Chen, C., Parker, A. M., Gidengil, C. A., & Matthews, L. J. (2020) · PLoS ONE · doi:10.1371/journal.pone.0239826 · Cited by 21
Realistic Aspects of Simulation Models for Fake News Epidemics over Social Networks
Lotito, Q. F., Zanella, D., & Casari, P. (2021) · Future Internet · doi:10.3390/fi13030076 · Cited by 21
Bots in Nets: Empirical Comparative Analysis of Bot Evidence in Social Networks
Schuchard, R., Crooks, A. T., Stefanidis, A., & Croitoru, A. (2018) · Studies in computational intelligence · doi:10.1007/978-3-030-05414-4_34 · Cited by 23
“Given that recent studies estimate that social bots account for 9–15% of all Twitter accounts [3, 4], it is essential to understand the implications associated with human and machine dialogue, either intentional or not.”
BackgroundUser Behavior Modelling for Fake Information Mitigation on Social Web
Rajabi, Z., Shehu, A., & Purohit, H. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-21741-9_24 · Cited by 21
The dynamics of Twitter users’ gun narratives across major mass shooting events
Lin, Y., & Chung, W. (2020) · Humanities and Social Sciences Communications · doi:10.1057/s41599-020-00533-8 · Cited by 20
“The presence of bots and elites, as shown to be influential in prior work (Varol et al., 2017; Rizoiu et al., 2018), can be a concern in our analysis as we aim to study the variation of narratives from a diverse set of users.”
BackgroundExtracting COVID-19 Events from TwitterPreprint
Zong, S., Baheti, A., Xu, W. H., & Ritter, A. (2020) · arXiv (Cornell University) · Cited by 21
A language framework for modeling social media account behavior
Nwala, A. C., Flammini, A., & Menczer, F. (2023) · EPJ Data Science · doi:10.1140/epjds/s13688-023-00410-9 · Cited by 31
Self-citationMajó-Vázquez, S., Congosto, M., Nicholls, T., & Nielsen, R. K. (2021) · Social Media + Society · doi:10.1177/20563051211027202 · Cited by 23
“The literature varies regarding the activity features and metadata assessed to detect automated accounts (see for instance Bastos & Mercea, 2019; Varol et al., 2017).”
BackgroundSocial Botomics: A Systematic Ensemble ML Approach for Explainable and Multi-Class Bot Detection
Dimitriadis, I., Georgiou, K., & Vakali, A. I. (2021) · Applied Sciences · doi:10.3390/app11219857 · Cited by 22
“[28] 1747/1291 826/657 Simple bots and humans”
BackgroundResultInfluentialImpact of correcting misinformation on social disruption
Iizuka, R., Toriumi, F., Nishiguchi, M., Takano, M., & Yoshida, M. (2022) · PLoS ONE · doi:10.1371/journal.pone.0265734 · Cited by 29
“For bot detection, methods using supervised learning generally give good results [14, 42].”
MethodEnvironmental Discourse Exhibits Consistency and Variation across Spatial Scales on Twitter
Chang, C. H., Armsworth, P. R., & Masuda, Y. J. (2022) · BioScience · doi:10.1093/biosci/biac051 · Cited by 20
“This threshold value was also supported by past research (Varol et al. 2017, Wojcik et al. 2018, Zhang et al. 2019). supplement's section 1.2.2 for more details.”
InfluentialKumble, S., Diddi, P., & Bien-Aimé, S. (2022) · Communication & Sport · doi:10.1177/21674795221124584 · Cited by 20
“Varol et al. (2017) “ estimate that the percentage of Twitter accounts exhibiting social bot behaviors is between 9% and 15% ” (p. 280).”
Manipulating Twitter through Deletions
Torres-Lugo, C., Pote, M., Nwala, A. C., & Menczer, F. (2022) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v16i1.19355 · Cited by 26
Self-citationLLMs Among Us: Generative AI Participating in Digital Discourse
Radivojevic, K., Clark, N., & Brenner, P. R. (2024) · Proceedings of the AAAI Symposium Series · doi:10.1609/aaaiss.v3i1.31202 · Cited by 31
Le, H., Boynton, G. R., Mejova, Y., Shafiq, Z., & Srinivasan, P. (2017) · ACM Conference on Hypertext and Social Media (HT) · doi:10.1145/3078714.3078736 · Cited by 20
“It is also noteworthy that a non-trivial amount of the collected tweets may come from bot accounts on Twitter [39].”
BackgroundCharacterizing Clickbaits on Instagram
Ha, Y.-I., Kim, J., Won, D., et al. (2018) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v12i1.15019 · Cited by 20
“In a similar context, a recent study has also reported that a considerable number of online social media accounts are in fact bots and that their activities are not real (Varol et al. 2017).”
BackgroundDetection of Fake Twitter Accounts with Machine Learning Algorithms
Aydın, İ., Sevi, M., & Salur, M. U. (2018) · International Artificial Intelligence and Data Processing Symposium (IDAP) · doi:10.1109/idap.2018.8620830 · Cited by 20
“Günümüzde aktif Twitter kullanıcıları arasında %15 oranında bot olduğu düşünülmektedir [4].”
Tweeting MPs: Digital Engagement between Citizens and Members of Parliament in the UK
Agarwal, P., Sastry, N., & Wood, E. (2019) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v13i01.3359 · Cited by 24
“For instance, if multiple people are managing an account, it has the potential to be detected as a bot by the Botometer tool [29, 30].”
BackgroundA Two-Phase Framework for Detecting Manipulation Campaigns in Social Media
Assenmacher, D., Clever, L., Pohl, J., Trautmann, H., & Grimme, C. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-49570-1_14 · Cited by 20
“Social Bots are considered very potent actors in the distribution of disinformation [10,11,14,18], and consequently, detection techniques for social bots have been (and still are) an important topic of research [9,10,13,20].”
BackgroundMethodYou Are Known by Your Friends: Leveraging Network Metrics for Bot Detection in Twitter
Beskow, D. M., & Carley, K. M. (2020) · Lecture notes in social networks · doi:10.1007/978-3-030-41251-7_3 · Cited by 21
McKinley, C. J., Olivier, E., & Ward, J. K. (2023) · Vaccines · doi:10.3390/vaccines11081319 · Cited by 20
Lee, S., Shin, D., Kwon, K. H., Han, S. P., & Lee, S. K. (2024) · MIS Quarterly · doi:10.25300/misq/2023/17195 · Cited by 20
Social Bot Detection Using Tweets Similarity
Wang, Y., Wu, C., Zheng, K., et al. (2018) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-01704-0_4 · Cited by 19
Emerging Complexity in Distributed Intelligent Systems
Guleva, V. Y., Shikov, E., Bochenina, K., Kovalchuk, S. V., Alodjants, A. P., & Boukhanovsky, A. V. (2020) · Entropy · doi:10.3390/e22121437 · Cited by 18
“Together with a deeper understanding of human–bot interaction [9,10], it leads to the idea that systems with AI agents and humans (expert, users, operators, etc.”
BackgroundUyheng, J., Ng, L. H. X., & Carley, K. M. (2021) · Computational and Mathematical Organization Theory · doi:10.1007/s10588-021-09332-1 · Cited by 23
“In this view, a shared concern in the field regards the extent to which information operations prove successful, how they achieve such success, and whether their dynamics can be understood in a systematic fashion (Shao et al. 2018; Varol et al. 2017).”
BackgroundFriendship Preference: Scalable and Robust Category of Features for Social Bot Detection
Moghaddam, S. H., & Abbaspour, M. (2022) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2022.3159007 · Cited by 23
“The supervised machine learning approaches rely on annotated datasets to distinguish between a bot and human accounts [13], [18], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42].”
BackgroundMethodInfluentialShould we agree to disagree about Twitter’s bot problem?
Varol, O. (2023) · Online Social Networks and Media · doi:10.1016/j.osnem.2023.100263 · Cited by 20
Self-citationAcker, A., & Kriesberg, A. (2017) · Proceedings of the Association for Information Science and Technology · doi:10.1002/pra2.2017.14505401001 · Cited by 19
“A recent study found that up to 15% of Twit-ter’s monthly active user accounts are bots with the ability to target specific platform users (Varol, Ferrara, Davis, Menczer, & Flammini, 2017).”
BackgroundHong, H., & Oh, H. J. (2020) · Sustainability · doi:10.3390/su12166515 · Cited by 18
Social Media and Microblogs Credibility: Identification, Theory Driven Framework, and Recommendation
Qureshi, K. A., Malick, R. A. S., & Sabih, M. (2021) · IEEE Access · doi:10.1109/access.2021.3114417 · Cited by 23
“There are almost 15-17% accounts which are bots [23], presenting human impersonation and perform many malicious and suspicious activities, e.g.: Spread of misinformation and fake news, fake support, fake product reviews, advertise for doubtful legality, hashtag, and other promotions, spread…”
BackgroundShevtsov, A., Tzagkarakis, C., Antonakaki, D., & Ioannidis, S. (2022) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v16i1.19349 · Cited by 18
“Various features are based on content (Ahmed and Abulaish 2013; Gilani, Kochmar, and Crowcroft 2017; Lee, Caverlee, and Webb 2010; Davis et al. 2016; Varol et al. 2017), sentiment (Loyola-González et al.”
BackgroundMethodInfluentialDetecting and Characterizing Bot-Like Behavior on Twitter
Qi, S., Alkulaib, L., & Broniatowski, D. A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-93372-6_26 · Cited by 19
Unsupervised detection of coordinated fake-follower campaigns on social media
Zouzou, Y., & Varol, O. (2024) · EPJ Data Science · doi:10.1140/epjds/s13688-024-00499-6 · Cited by 25
Self-citationPerceived threats from social bots: The media's role in supporting literacy
Schmuck, D., & von Sikorski, C. (2020) · Computers in Human Behavior · doi:10.1016/j.chb.2020.106507 · Cited by 20
Comparing the Impact of Social Media Regulations on News Consumption
Etta, G., Cinelli, M., Galeazzi, A., Valensise, C. M., Quattrociocchi, W., & Conti, M. (2022) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2022.3171391 · Cited by 25
“Extensive use of bots was made to manipulate the public debate through the spreading of fake news [57], [58].”
BackgroundVrana, V. G., Kydros, D. A., Kotzaivazoglou, I., et al. (2023) · Sustainability · doi:10.3390/su15021322 · Cited by 18
Supervised learning models for social bot detection: Literature review and benchmark
Nguyen, H.-D., Nguyen, Q. D., Nguyen, C.-D. T., To, P. T., Nguyen, D. H., Nguyen-Gia, H., Tran, L. H., Tran, A. Q., Dang-Hieu, A., Nguyen‐Duc, A., et al. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122217 · Cited by 20
AbuSniff: Automatic Detection and Defenses Against Abusive Facebook Friends
Talukder, S., & Carbunar, B. (2018) · International Conference on Web and Social Media · doi:10.1609/icwsm.v12i1.14995 · Cited by 23
“Such stranger friends could be bots (Varol et al. 2017) that passively collect sensitive user data and later use it against the user’s best interest, as we also show through pilot study answers.”
BackgroundModeling Analytical Streams for Social Business Intelligence
Lanza-Cruz, I., Berlanga, R., & Aramburu, M. J. (2018) · Informatics · doi:10.3390/informatics5030033 · Cited by 17
Hawkes Process for Understanding the Influence of Pathogenic Social Media Accounts
Alvari, H., & Shakarian, P. (2019) · International Conference on Data Intelligence and Security (ICDIS) · doi:10.1109/icdis.2019.00013 · Cited by 19
“The work of [35] presents a supervised framework for bot detection which uses more than thousands features.”
BackgroundDetection of Fake Users in Twitter Using Network Representation and NLP
Chakraborty, M., Das, S., & Mamidi, R. (2022) · International Conference on Communication Systems & Networks (COMSNETS) · doi:10.1109/comsnets53615.2022.9668371 · Cited by 23
“Varol et. al [22] used public data to extract around a thousand features about users: followers, follow-ings, interactions and other activities and identified different types of accounts, including self promotions, spamming and fake news spreading accounts.”
BackgroundAutomated Identification of Social Media Bots Using Deepfake Text Detection
Saravani, S. M., Ray, I., & Ray, I. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-92571-0_7 · Cited by 18
“Some studies report that 9 to 20% of Twitter users are bots and they contribute to 35% of Twitter’s total contents [1,25].”
BackgroundSupervised Classification of Twitter Accounts Based on Textual Content of Tweets.
Johansson, F. (2019) · CLEF (Working Notes) · Cited by 17
Ruiz-Frau, A., Ospina-Alvarez, A., Villasante, S., Pita, P., Maya-Jariego, I., & de Juan, S. (2020) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · Cited by 17
Characteristics of the vegetable oil debate in social-media and its implications for sustainability
Candellone, E., Aleta, A., de Arruda, H. F., et al. (2024) · Communications Earth & Environment · doi:10.1038/s43247-024-01545-x · Cited by 17
“This characteristic of the platform is unfortunately leveraged by certain groups to spread false news and misinformation 26,27 .”
User Personas and Social Media Profiles
Humphrey, A. S. (2017) · Persona Studies · doi:10.21153/ps2017vol3no2art708 · Cited by 17
Posting Bot Detection on Blockchain-based Social Media Platform using Machine Learning Techniques
Kim, T., Shin, H., Hwang, H. J., & Jeong, S. (2021) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v15i1.18062 · Cited by 16
“Many researchers have tried to detect bots with machine learning algorithms (Abu-El-Rub and Mueen 2019; Chu et al. 2012; Clark et al. 2016; Dickerson, Kagan, and Subrahmanian 2014; Santia, Mujib, and Williams 2019; Varol et al. 2017; Wang 2010).”
BackgroundMalicious Bot Detection in Online Social Networks: Arming Handcrafted Features with Deep Learning
Mou, G., & Lee, K. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60975-7_17 · Cited by 22
“They come from various sources [13–16, 23, 30, 33, 39, 42, 43] and contain many types of users (content polluters, fake accounts, traditional & social spambots, stock related bots, political bots, fake followers, verified accounts, celebrity accounts, legitimate users, etc.).”
BackgroundText Analysis Methods for Misinformation–Related Research on Finnish Language Twitter
Jussila, J., Suominen, A. H., Partanen, A., & Honkanen, T. (2021) · Future Internet · doi:10.3390/fi13060157 · Cited by 17
“In particular, the rapid spread of false information on Twitter has caused concern [3,17,18].”
BackgroundA Comparative Study of Bot Detection Techniques With an Application in Twitter Covid-19 Discourse
Antenore, M., Camacho, J. M., & Panizzi, E. (2022) · Social Science Computer Review · doi:10.1177/08944393211073733 · Cited by 21
“(Varol et al., 2017) developed a supervised method with more than 1000 features related to user metadata, friends, network, temporal, content, and sentiment.”
Influential
Metadata
- Authors
- Varol, O., Ferrara, E., Davis, C., Menczer, F., & Flammini, A.
- Affiliations
- Indiana University (US)
- University of Southern California (US)
- Venue
- Proceedings of the International AAAI Conference on Web and Social Media
- Published
- 2017-05-03
- Volume
- 11
- Issue
- 1
- Pages
- 280-289
- ISSN
- 2162-3449 (ISSN-L)
- 2334-0770
- OpenAlex
- W2595521492
- Semantic Scholar
- 6a025e1e4d7269b20dadc91e14f28a93124fc145
- Cited by
- 981
- References
- 71
- Citations by year
- 2026: 90 · 2025: 81 · 2024: 84 · 2023: 105 · 2022: 96 · 2021: 103 · 2020: 164 · 2019: 126 · 2018: 104 · 2017: 28
- FWCI
- 75.86
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Proceedings of the International AAAI Conference on Web and Social Media (publishedVersion)
- Funders
- National Science Foundation (1101743)
- James S. McDonnell Foundation
- Defense Advanced Research Projects Agency (W911NF-12-1-0037)
- Office of Naval Research (N15A-020-0053)
- Topics
- Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Keywords
- social bots, bot detection, Twitter, human-bot interaction, botnets, spammer account, self-promotion, user activity patterns, social media
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
