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 601–700 of 933
Beutel, I., Kirschler, O., & Kokott, S. (2022) · Central and Eastern European eDem and eGov Days · doi:10.24989/ocg.v.342.2 · Cited by 3
Identification of Bots and Cyborgs in the #FeesMustFall Campaign
Khan, Y., Thakur, S. C., Obiyemi, O. O., & Adetiba, E. (2022) · Informatics · doi:10.3390/informatics9010021 · Cited by 4
Cross-Domain Pseudo-Sensors in IBSM
Hintz, K. J., Williamson, W., Brannon, S., et al. (2018) · International Conference on Information Fusion (FUSION) · doi:10.23919/icif.2018.8455569 · Cited by 3
“For example, feature sets constructed from this metadata have been used to detect the use of bots in political influence campaigns [30].”
Foysal, A., Islam, S., & Rahaman, T. (2019) · International Journal of Computer Applications · doi:10.5120/ijca2019919701 · Cited by 3
“Varol [14], extracted 1150 features based on their framework and divided them into six sections.”
MethodInside the Tool Set of Automation: Free Social Bot Code Revisited
Assenmacher, D., Adam, L., Frischlich, L., Trautmann, H., & Grimme, C. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-39627-5_9 · Cited by 4
Are Bots Humans? Analysis of Bot Accounts in 2019 Indian Lok Sabha Elections (Workshop Paper)
Hitkul, H., Gurjar, O., Sadaria, A., Gupta, K., Srikanth, S., Shah, R. R., & Kumaraguru, P. (2020) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm50055.2020.00073 · Cited by 3
“We decided to use the Botometer API [23] to classify users into the Bots or Humans due to its popularity in literature [6], [24], [11] and continuous improvements [25].”
MethodIs It Digital Entrepreneurship? Designing a New Sport through Audience Ethnography
Leung, L., & Feldman, D. (2021) · Sustainability · doi:10.3390/su132111690 · Cited by 3
Optimal structure of groups under exposure to fake news
Berekméri, E., Derényi, I., & Zafeiris, A. (2019) · Applied Network Science · doi:10.1007/s41109-019-0227-z · Cited by 3
“…of social bots or trolls who often speed up the process of spreading false information to the same order of magnitude as the propagation of reliable information (Vosoughi et al. 2018; Shao et al. 2018;MitchellWaldrop 2017; Pennycook and Rand 2019; Bovet and Makse 2019; Varol et al. 2017).”
BackgroundGenerating Spoofing Tweets considering Points of Interest of Target User
Lim, J., Nitta, N., Nakamura, K., & Babaguchi, N. (2019) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc47483.2019.9023353 · Cited by 3
“For example, the ratio of the bot accounts on Twitter is estimated between 9 and 15% [1].”
BackgroundBerman, R., Melumad, S., Humphrey, C., & Meyer, R. J. (2017) · SSRN Electronic Journal · doi:10.2139/ssrn.2905484 · Cited by 3
On-the-fly Detection of Autogenerated TweetsPreprint
Lundberg, J., Nordqvist, J., & Matosevic, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.01197 · Cited by 5
“The additional attribute retweetRatio reveals that there are many AGTs that mostly retweet in order to spread some idea or advertisement (Varol et al. 2017).”
BackgroundHow many bots are you following?Preprint
Balestrucci, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.05222 · Cited by 3
“The information diffusion on OSM is often supported by automated accounts controlled, totally (bots) or partially (cyborg), by ad-hoc software applications [45].”
BackgroundMethodCombating Disinformation in a Social Media AgePreprint
Shu, K., Bhattacharjee, A., Alatawi, F., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.07388 · Cited by 3
“Words, phrases (Varol et al., 2017), and topics (Morstatter et al., 2016) of social media posts can be a strong indicator of bot activity.”
BackgroundCharacterizing User Susceptibility to COVID-19 Misinformation on TwitterPreprint
Teng, X., Lin, Y., Chung, W., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.09532 · Cited by 3
“Following prior studies (Varol et al. 2017; Grinberg et al. 2019), we labelled bots at thresholds 0.5 and 0.7: an account was considered to be a bot if its Botometer score were above 0.5 or 0.7.”
BackgroundMethodInfluentialDecentralized Discourse: Interaction Dynamics on Mastodon
Brauweiler, M., Chaitanya, M., Pfeffer, J., & Brandes, U. (2025) · ACM Web Science Conference (WebSci) · doi:10.1145/3717867.3717887 · Cited by 2
“Mastodon also exhibits a more balanced follower distribution and significantly fewer social bots (5% compared to Twitter’s 15% [9, 13]), along with distinct disassortative properties.”
Demystifying Misconceptions in Social Bots Research
Cresci, S., Yang, K.-C., Spognardi, A., Pietro, R. D., Menczer, F., & Petrocchi, M. (2025) · Social Science Computer Review · doi:10.1177/08944393251376707 · Cited by 30
“These claims can only be made by omitting a significant amount of literature (Varol et al., 2017; Yang et al., 2019, 2020; Sayyadiharikandeh et al., 2020; Cresci, 2020).”
Self-citationA Primer on Temporal Graph Learning
Rahman, A. U., Elhag, A. A., & Coon, J. P. (2025) · ACM Computing Surveys · doi:10.1145/3771693 · Cited by 7
“The temporal activity of specific users can also be analyzed to identify bot accounts [Varol et al. 2017] on a social media platform.”
Machine Learning Based Detection of Denial of Wallet Attacks in Serverless Computing
Ghaleh, A. M., & Kashi, S. S. (2025) · SN Computer Science · doi:10.1007/s42979-025-04545-6 · Cited by 3
Wass, L. M., Wu, Z., Vizoso, J., Wu, J. T. K., & Lin, L. K. (2026) · Journal of Medical Internet Research · doi:10.2196/80346 · Cited by 4
“Past estimates suggest between 9% to 15% of active X users have automated accounts [53].”
Does generative AI mean the end for online ethnography?
Hine, C. (2026) · Methodological Innovations · doi:10.1177/20597991261443793 · Cited by 2
“…release to the public in 2022, chatbots that simulated human-generated content were already widespread: using a machine learning approach applied to archived data from Twitter in 2015, Varol et al. (2017) suggested that between 9% and 15% of active Twitter accounts at that point were bots.”
Cybersecurity: Balancing Efficiency with Long-Term Resilience in Connected Ecosystems
Reischuk, R. M. (2021) · Springer eBooks · doi:10.1007/978-3-030-76897-3_13 · Cited by 2
Han, N., Huang, H., Wang, J., Shi, B., & Li, R. (2022) · Complexity · doi:10.1155/2022/4733305 · Cited by 3
“Indeed, social bots account for about 9% to 15% of active Twitter accounts [8].”
The Effect of COVID-19 on the Origins of Florida State Park Visitors and Online Reviewers
OWUOR, I., Hochmair, H. H., & Paulus, G. (2022) · AGILE GIScience Series · doi:10.5194/agile-giss-3-50-2022 · Cited by 2
“The integrity of social media geodata is affected by various factors such as automated content generated through bots which on platforms such as Twitter is estimated to be at least 9% of its accounts (Varol et al., 2017).”
Detection Technology of Social Robot: Based on the Interpretation of Botometer Model
Tian, J., Huang, Y.-T., & Zhang, D. (2022) · Journal of Computer Science and Technology Studies · doi:10.32996/jcsts.2022.4.2.6 · Cited by 2
Addressing the Methodological Challenges that Cloaked Profiles Pose to Digital Observations
Rabe, T. N. (2022) · Journal of Contemporary Ethnography · doi:10.1177/08912416221135498 · Cited by 2
“The Observatory on Social Media at Indiana University has developed “Botometer,” “Hoaxy,” and “Botslayer” as useful tools to help discern with relative certainty if online profiles are performing automated actions, are part of a network, or if they are administered by a human (Varol et al. 2017).”
BackgroundKats, D., & Sharif, M. (2022) · International Conference on Human-Agent Interaction (HAI) · doi:10.1145/3527188.3561928 · Cited by 3
“estimated that 9%–15% of active Twitter accounts are bots [54].”
BackgroundHuman–agent interaction as augmentation of social intelligence
Ōsawa, H. (2023) · Artificial Life and Robotics · doi:10.1007/s10015-023-00874-y · Cited by 3
“The result, however, was that the political stance of the entire population to which the bot was introduced shifted more to the left than to the right [4].”
BackgroundFake Twitter Followers Detection using Machine Learning Approach
Shabbir, M. Z., Naseer, I., Akhter, S., Abubakar, M., Issa, G. F., & Mehmood, M. H. (2023) · International Conference on Business Analytics for Technology and Security (ICBATS) · doi:10.1109/icbats57792.2023.10111260 · Cited by 2
“[24] proposed a supervised machine learning approach to detect”
BackgroundOn the Design of a Misinformation Widget (MsW) Against Cloaked Science
Arroyo, D., Esposti, S. D., Espés, A. G., Palmero, S., & Pérez-Miguel, L. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-39828-5_21 · Cited by 2
Optimizing Effort Estimation in Agile Software Development: Traditional vs. Advanced ML Methods
Sunda, N., & Sinha, R. R. (2023) · International Conference on Communication, Security and Artificial Intelligence (ICCSAI) · doi:10.1109/iccsai59793.2023.10421235 · Cited by 5
“The majority of AI work in recent years has been driven by ML techniques [12-13].”
BackgroundBeyond Following: Augmenting Bot Detection with the Integration of Behavioral Patterns
Reiche, S., Cohen, S., Simonov, K., & Friedrich, T. (2024) · Studies in computational intelligence · doi:10.1007/978-3-031-53468-3_21 · Cited by 2
role of social bots in the Brazilian environmental debate:
Salles, D., de Medeiros, P. M., Martins, B., Regattieri, L. L., & Santini, R. M. (2024) · The International Review of Information Ethics · doi:10.29173/irie510 · Cited by 2
Elayan, S., & Sykora, M. D. (2024) · Journal of Computational Social Science · doi:10.1007/s42001-024-00314-2 · Cited by 4
“Botometer produced a bot likelihood score, as well as six subscores (e.g., social network, timing…, see [94]) to help identify which features contributed most to the overall account automation score.”
InfluentialAdversarial botometer: adversarial analysis for social bot detection
Najari, S., Rafiei, D., Salehi, M., & Farahbakhsh, R. (2024) · Social Network Analysis and Mining · doi:10.1007/s13278-024-01387-7 · Cited by 2
“In 2017, the average presence of bots on active Twitter accounts was estimated to be around 15% [1], while on Facebook, it was approximately 11% in 2019 [2].”
Twitter (X) Spam Detection Using Natural Language Processing by Encoder Decoder Model
Asha, S., Madhan, M., B, H. K. P., Hariharan, S. G., Dharaneesh, B., & Sai Jeet, K. (2024) · International Conference on Sustainable Computing and Integrated Communication in Changing Landscape of AI (ICSCAI) · doi:10.1109/icscai61790.2024.10866112 · Cited by 2
Social Media Influencers and Politics
Makse, H. A., & Zava, M. (2024) · Understanding complex systems · doi:10.1007/978-3-031-78058-5_2 · Cited by 3
Gong, X., Cai, M., Meng, X., Yang, M., & Wang, T. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2470292 · Cited by 2
“Humans are no longer the only participants in the media ecosystem, and social bots have penetrated it (Shi & Chen, 2020; Varol et al., 2017).”
Makovi, K., Bonnefon, J., Oudah, M., Sargsyan, A., & Rahwan, T. (2025) · iScience · doi:10.1016/j.isci.2025.112833 · Cited by 3
“For example, machines can account for 1%– 15% of users on social media platforms such as X, formerly known as Twitter, 56,57 and generate a disproportionate amount of content on important topics, such as climate, 58 vaccines, 59 and religious tensions.”
SOSYAL BOT ALGILAMA TEKNİKLERİ VE ARAŞTIRMA YÖNLERİ ÜZERİNE BİR İNCELEME
Karataş, A., & Şahin, S. (2018) · ULUSLARARASI BİLGİ GÜVENLİĞİ MÜHENDİSLİĞİ DERGİSİ · doi:10.18640/ubgmd.348517 · Cited by 2
Advanced Models for Stylometric Applications
Savoy, J. (2020) · Springer eBooks · doi:10.1007/978-3-030-53360-1_7 · Cited by 3
SaraBotTagger - A Light Tool to Identify Bots in Twitter
Barbosa, C. M. G., Félix, L. G. D. S., Alves, A. P. S., Xavier, C. R., & Vieira, V. D. F. (2021) · Studies in computational intelligence · doi:10.1007/978-3-030-65351-4_9 · Cited by 2
Dias, F. D. V., & de Morais, D. F. (2021) · Revista Thesis Juris · doi:10.5585/rtj.v10i1.17210 · Cited by 2
Social Bots als Stimmen im Diskurs
Dreesen, P., & Krasselt, J. (2022) · De Gruyter eBooks · doi:10.1515/9783110721447-014 · Cited by 3
Alperín, J. P., Hanson, E. W., Shores, K., et al. (2017) · doi:10.1145/3097286.3097313 · Cited by 2
“, bot) accounts themselves (estimated between 9-15% of active Twitter accounts) [21].”
BackgroundNishihara, Y., Ikuta, M., Yamanishi, R., & Fukumoto, J. (2017) · IIAI International Congress on Advanced Applied Informatics (IIAI-AAI) · doi:10.1109/iiai-aai.2017.68 · Cited by 2
Twitter: More than 140 Characters
Barnard, S. R. (2018) · Springer eBooks · doi:10.1007/978-3-319-90446-7_2 · Cited by 2
An Approximately Optimal Bot for Non-Submodular Social Reconnaissance
Smith, J. D., Kuhnle, A., & Thai, M. T. (2018) · ACM Conference on Hypertext and Social Media (HT) · doi:10.1145/3209542.3209553 · Cited by 2
Kušen, E., & Strembeck, M. (2018) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1109/asonam.2018.8508275 · Cited by 2
Identity deception detection: requirements and a model
van der Walt, E., & Eloff, J. H. P. (2019) · Information and Computer Security · doi:10.1108/ics-01-2019-0017 · Cited by 2
Fighting Disinformation Online: Building the Database of Web Tools
Kavanagh, J., Cherney, S., Reininger, H., & Griffin, N. (2020) · RAND Corporation eBooks · doi:10.7249/rr3000 · Cited by 2
Twitter Bots and the Swedish Election
Fernquist, J., Kaati, L., Schroeder, R., Akrami, N., & Cohen, K. (2020) · Lecture notes in social networks · doi:10.1007/978-3-030-41251-7_6 · Cited by 2
Analyzing the Existence of Organization Specific Languages on Twitter
Sánchez, R., Zubiaga, A., & Almeida, A. (2021) · IEEE Access · doi:10.1109/access.2021.3102865 · Cited by 3
“Researchers in this area focused on creating frameworks that, using features from Twitter users, can identify if they are malicious users [25]–[28].”
BackgroundA variational-autoencoder approach to solve the hidden profile task in hybrid human-machine teams
Pescetelli, N., Reichert, P., & Rutherford, A. (2022) · PLoS ONE · doi:10.1371/journal.pone.0272168 · Cited by 4
Bullyproof Sentinel: Fortifying Online Spaces Against Bullying using Machine Learning
Dilshani, M. M. T., Vinoshan, T., Wijesinghe, W. A. S. D., et al. (2023) · International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC) · doi:10.1109/i-smac58438.2023.10290419 · Cited by 2
“The study highlights the significant role bots play in influencing public opinion and revealing individuals responsible for misleading information distribution [4].”
BackgroundBalancing the Scales: HyperSMOTE for Enhanced Hypergraph Classification
Alkulaib, L., & Lu, C. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386107 · Cited by 2
“Traditional supervised methods relied on annotated datasets, but their static nature made them susceptible to evolving bot behaviors [5], [11], [12].”
MethodA Fistful of Votes: Understanding the Voting System in Social Question and Answer Websites
Zhang, J. J., Labiod, H., & Meng, W. (2019) · IFIP International Conference on New Technologies, Mobility and Security (NTMS) · doi:10.1109/ntms.2019.8763775 · Cited by 2
“For example, HP has reported that nearly half of retweets are from spams in Sina weibo [9], and at least there are at least 15% spams in twitter in a conservative estimation [10].”
BackgroundFake News Mitigation in Social Networks
Lacombe, R. (2018) · KTH Publication Database DiVA (KTH Royal Institute of Technology) · Cited by 2
Brown, N. (2019) · University of Groningen research database (University of Groningen / Centre for Information Technology) · doi:10.33612/diss.99196913 · Cited by 1
"Let's Eat Grandma": When Punctuation Matters in Sentence Representation for Sentiment Analysis.Preprint
Karami, M., Mosallanezhad, A., Mancenido, M. V., & Liu, H. (2021) · arXiv (Cornell University) · Cited by 2
LGBTQ Visibility Measured Consistently and Persistently in US Twitter Bios from 2012 through 2023Preprint
Jones, J. J., & Cisternino, I. (2022) · doi:10.31235/osf.io/mcax8 · Cited by 2
Sadeghi, N., & Riahi, N. (2023) · Research Square · doi:10.21203/rs.3.rs-2556040/v1 · Cited by 2
Lindner, I., Heidergott, B., Badri, S., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4851284 · Cited by 2
Discrete Opinion Dynamics with Social Bots on Signed Network
Luo, Y., Cheng, C. C. L., & Yu, C. B. (2020) · Chinese Control Conference (CCC) · doi:10.23919/ccc50068.2020.9188793 · Cited by 1
“About 9%-15% percent of Twitter accounts are social bots[6] and the report of Face-book in 2017 shows there exist 100,000 monthly active bots on the message platform[7].”
BackgroundBeyond Words: Comparing Structure, Emoji Use, and Consistency Across Social Media Posts
Swartz, M., Crooks, A. T., & Croitoru, A. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-61255-9_1 · Cited by 1
Agency in Computer-Mediated Communication: Bots and US Political Elections
Piercy, C. W., Bisel, R. S., & Treem, J. W. (2022) · Emerald Group Publishing Limited eBooks · doi:10.1108/978-1-80071-597-420221032 · Cited by 1
Dhoka, A., Pachauri, S., Nigam, C., & Chouhan, S. (2023) · International Conference on Electronics and Renewable Systems (ICEARS) · doi:10.1109/icears56392.2023.10085565 · Cited by 1
“In recent years, ML approaches have driven most of the development in AI [18-19].”
BackgroundA Fuzzy Logic-Based Opinion Update Model for Online Social Networks with Influential Social Bots
Rout, R. R., Sahana, S., & Parimi, P. (2024) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic60209.2024.10463323 · Cited by 1
“Studies show that only humans tend to show this follower behavior, whereas bots do not change their opinion with time [12].”
BackgroundVarma, M. A., & Kshirsagar, M. (2024) · INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · doi:10.55041/ijsrem36608 · Cited by 2
Easy-access online social media metrics are associated with misinformation sharing activity
Számely, J., Galeazzi, A., Koltai, J., & Omodei, E. (2025) · Scientific Reports · doi:10.1038/s41598-025-25049-6 · Cited by 1
Posted in Error: Did the CDC’s Retraction of Aerosol Guidance Undercut Its Public Reputation?
Hong, T. J., Tang, Z., Wu, J., Murray, E. J., Wijaya, D. T., & Beaudoin, C. E. (2024) · Journal of Health Communication · doi:10.1080/10810730.2024.2427943 · Cited by 1
An Analysis of Relationship Between Social Bots and Echo Chambers on X in Modern Japan
Ippa, S., Okubo, T., & Hashimoto, M. (2024) · International Symposium on Computing and Networking · doi:10.1109/candar64496.2024.00014 · Cited by 2
“Botometer has been used in many studies [9] [12] [28] [29] [30] [31] [32] [33], including disinformation analysis about COVID-19 [34], and is considered a trusted tool in social bot detection.”
InfluentialKelly-Thompson, K., Weldon, S. L., Wright, J. M., Goldwasser, D., Einwohner, R. L., Sinclair‐Chapman, V., & Tormos‐Aponte, F. (2025) · Politics Groups and Identities · doi:10.1080/21565503.2025.2453167 · Cited by 2
“Moreover, focusing on the most active users allowed us to analyze the most reinforced and stable relationships of engagement between identifiable users, thus avoiding “bots” or fake accounts (Varol et al. 2017).”
Unmasking social bots: how confident are we?
Giroux, J., Ariyarathne, G., Nwala, A. C., & Fanelli, C. (2025) · EPJ Data Science · doi:10.1140/epjds/s13688-025-00536-y · Cited by 6
“Alternatively, all of these feature types are combined into a single model [4, 16, 21, 31, 46, 53, 57].”
From Intangible Heritage to Virtual Play: Bridging Immersive Experience and Social Play in VR
Hsu, C.-C., Luo, H.-Y., Shen, Y., et al. (2025) · Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3720013 · Cited by 1
“A large amount of studies have proposed that sociability is one of the most important factors in game experience[12, 19].”
Bilgi Çarpıtma Sürecinde Yapay Zekanın İşlevi
Alpsoy, İ. (2025) · Erciyes İletişim Dergisi · doi:10.17680/erciyesiletisim.1636521 · Cited by 1
Debanath, K., Aich, S., & Srizon, A. Y. (2025) · 2025 2nd International Conference on Next-Generation Computing, IoT and Machine Learning (NCIM) · doi:10.1109/ncim65934.2025.11160229
“Traditional bot activity metrics, such as retweet counts [12], fail to capture evolving manipulation strategies.”
InfluentialAl-Zaman, M. S. (2025) · Social Science Computer Review · doi:10.1177/08944393251400281 · Cited by 1
A Community-Aware Spatio-Temporal Hypergraph Contrastive Learning Method for Social Bot Detection
Liu, F., Li, Z., & Ma, R. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3637684 · Cited by 1
“It is estimated that bots account for approximately 15% of active users on Twitter, meaning a substantial portion of daily social interactions may be driven by bots [1].”
Saucier, C. J., Wack, M., Linvill, D. L., Okoronkwo, A. H., Tatineni, G., & Sezgin, A. (2025) · Computers in Human Behavior · doi:10.1016/j.chb.2025.108881 · Cited by 2
Simulating Advanced Social Botnets: A Framework for Behavior Realism and Coordinated Stealth
Jin, R., & Liao, Y. (2025) · Information · doi:10.3390/info17010027 · Cited by 1
Don't You Know That You're Toxic? How Influencer‐Driven Misinformation Fuels Online Toxicity
Domenico, G. D., Mangiò, F., & Dineva, D. (2026) · Psychology and Marketing · doi:10.1002/mar.70106 · Cited by 1
“Also, to make sure that our comment corpus was not affected by potential trolls or social bots' activities, we conducted a thorough bot‐detection analysis based on content, time, and account‐based measures (Varol et al. 2017).”
Mohammadi, N., Maghsoudi, M., & Abarghouezade, Z. (2026) · Computing · doi:10.1007/s00607-026-01634-z · Cited by 2
Artificially intelligent opinion polling
Cerina, R., & Duch, R. M. (2026) · Royal Society Open Science · doi:10.1098/rsos.251150 · Cited by 1
Engineering collective attention in the age of artificial intelligence
Zhu, R. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01084-8 · Cited by 1
SOCIAL MEDIA BOT ACCOUNT DETECTION MODEL BASED ON MULTI-VIEW METHOD WITH ATTENTION MECHANISM
Buchyk, S., & PIATYHOR, V. (2026) · Cybersecurity Education Science Technique · doi:10.28925/2663-4023.2026.32.1168 · Cited by 1
Xin, J., Zheng, L., & Ni, W. (2026) · Big Data & Society · doi:10.1177/20539517261442369 · Cited by 2
“Research on social bots documented how automated or semi-automated accounts could simulate engagement, amplify preferred frames, and manufacture consensus at scale (Ferrara et al., 2016; Woolley and Howard, 2016; Varol et al., 2017).”
Toward an Integrated RAT-STT Framework for Understanding Cybercrime in the Age of AI
Congo, V. T., & Choi, J. J.-H. (2026) · Journal of Social Science · doi:10.16881/jss.2026.04.37.2.123 · Cited by 1
A Hybrid Approach Combining Network Analysis and Deep Learning for Instagram Political Bot Detection
Badami, H., Mateos, C., Hirsch, M., et al. (2026) · ACM/SIGAPP Symposium on Applied Computing (SAC) · doi:10.1145/3748522.3779720 · Cited by 1
“This same assumption was made by [8], when they were preparing the dataset of Twitter bots that was used for developing the famous bot detection tool Botometer [26], a successful model used in a huge percentage of the literature, confirming the validity for our assumption.”
Banikalef, A. A. A., & Mehawesh, M. I. (2026) · Social Media + Society · doi:10.1177/20563051261454774 · Cited by 1
“Studies on bots and automation reveal a core problem: automated classifiers err when language and platform behavior vary (Cresci, 2020; Ferrara et al., 2016; Varol et al., 2017).”
Building Reference Datasets to Support Socialbots Detection
Pacheco, C. C., Garcia, A. D. V., Machado, R., & Salles, R. M. (2018) · IEEE International Workshop on Metrology for Industry 4.0 & IoT (MetroInd4.0&IoT) · doi:10.1109/metroi4.2018.8428331 · Cited by 1
“[10] (3,000 accounts).”
Online Monitoring of Large Events
Fernquist, J., & Kaati, L. (2018) · European Intelligence and Security Informatics Conference · doi:10.1109/eisic.2018.00015 · Cited by 1
“In [16] it is suggested that between 9% and 15% of active Twitter accounts are bots.”
BackgroundAre There Bots even in FIFA World Cup 2018 Tweets?
Bagarish, M., Alshammari, R., & Zincir-Heywood, N. (2019) · International Conference on Network and Service Management (CNSM) · doi:10.23919/cnsm46954.2019.9012743 · Cited by 1
“The tool has been improved by the work presented by Varol et al. [2].”
BackgroundMethodInfluentialKuzmin, V. N., Менисов, А. Б., & Shastun, I. A. (2020) · Бизнес-информатика · doi:10.17323/2587-814x.2020.3.54.66 · Cited by 1
Detecting Abnormal Social Network Accounts with Hurst of Interest Distribution
Wang, X., Sui, Y., Tao, Y., Zhang, Q., & Wei, J. (2021) · Security and Communication Networks · doi:10.1155/2021/6653430 · Cited by 1
“There are no public datasets that were used in the related research on the detection of compromised accounts, so it is difficult to accurately determine whether an account has been compromised or not. varol-2017 dataset used by Varol et al. [36] was selected in the present work.”
MethodMachine-Human Interaction: A Paradigm Shift?
Saint-Louis, H. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-78462-1_9 · Cited by 1
Online identity as a collective labeling process
Barron, A. T. J., ten Thij, M., & Bollen, J. (2023) · Journal of Physics Complexity · doi:10.1088/2632-072x/acc62c · Cited by 1
Twitter Bots in Cyber-Physical-Social Systems: Detection and Estimation Based on the SEIR Model
Zhang, W., Lu, J., Liu, Y., et al. (2023) · Security and Communication Networks · doi:10.1155/2023/6234030 · Cited by 1
Yanlış Bilgi Ve Dezenformasyonla Mücadele: Kavramlar Ve Uygulamalar
MUTLU, N. (2023) · Uluslararası Sosyal Bilimler Akademi Dergisi · doi:10.47994/usbad.1257491 · Cited by 4
Detecting Camouflaged Social Bots Through Multi-level Aggregation and Information Encoding
Wang, Z., & Zhao, K. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-7241-4_25 · Cited by 1
Saeed, M. H., Ali, S., Paudel, P., Blackburn, J., & Stringhini, G. (2024) · International Symposium on Research in Attacks, Intrusions and Defenses (RAID) · doi:10.1145/3678890.3678911 · Cited by 3
“Numerous studies have examined the role of social bots in the spread of political disinfor-mation [7], [19], [20], [57].”
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
