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 401–500 of 933
FraudJudger: Fraud Detection on Digital Payment Platforms with Fewer Labels
Deng, R., Ruan, N., Zhang, G., & Zhang, X. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-41579-2_33 · Cited by 11
“Some researchers focus on analyzing user’s social networks to find suspicious behaviors [4] [19] by graph models.”
BackgroundPedrazzi, S., & Oehmer, F. (2020) · Journal of Information Policy · doi:10.5325/jinfopoli.10.2020.0549 · Cited by 12
Explainable Artificial Intelligence for Authorship Attribution on Social Media
Theóphilo, A., Padilha, R., Andaló, F., & Rocha, A. D. R. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746262 · Cited by 11
A Reverse Turing Test for Detecting Machine-Made Texts
Shao, J., Uchendu, A., & Lee, D. (2019) · ACM Conference on Web Science (WebSci) · doi:10.1145/3292522.3326042 · Cited by 10
“Related, [16] used meta data in a cluster model to find strong predictors for social bots in twitter.”
MethodA Tensor Based Data Model for Polystore
Leclercq, É., & Savonnet, M. (2018) · International Database Engineering & Applications Symposium (IDEAS) · doi:10.1145/3216122.3216152 · Cited by 10
Measuring user relevance in online debates through an argumentative model
Alsinet, T., Argelich, J., Béjar, R., et al. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.02.008 · Cited by 10
Diffusion of competing rumours on social media
Kaligotla, C., Yücesan, E., & Chick, S. E. (2020) · Journal of Simulation · doi:10.1080/17477778.2020.1785345 · Cited by 11
“One study estimated that 15% of Twitter ’s user base consisted of bots (Varol et al., 2017, May).”
BackgroundAnalysing centralities for organisational role inference in online social networks
Sánchez, R., Bilbao-Jayo, A., Zulaika, U., & Almeida, A. (2020) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2020.104129 · Cited by 10
How Epidemic Psychology Works on Social Media: Evolution of responses to the COVID-19 pandemicPreprint
Aiello, L. M., Quercia, D., Zhou, K., Constantinides, M., Šćepanović, S., & Joglekar, S. P. (2020) · arXiv (Cornell University) · Cited by 10
Evolution of Malicious Social Bot Detection: From Individual Profiling to Group Analysis and Beyond
Liu, Y., Xu, S., Li, Y., & Yu, S. (2025) · Journal of Social Computing · doi:10.23919/jsc.2025.0017 · Cited by 9
Social media bot detection using Dropout-GAN
Shukla, A., Jureček, M., & Stamp, M. (2024) · Journal of Computer Virology and Hacking Techniques · doi:10.1007/s11416-024-00521-5 · Cited by 12
“This work was later expanded upon in [30] where the authors trained the model on a new dataset, and demonstrated which features they leveraged in their technique.”
Suárez-Lledó, V., Ortega‐Martin, E., Carretero-Bravo, J., Ramos-Fiol, B., & Álvarez‐Gálvez, J. (2024) · JMIR Infodemiology · doi:10.2196/50021 · Cited by 10
Agents of Discord: Modeling the Impact of Political Bots on Opinion Polarization in Social Networks
Lu, H.-C., & Lee, H. (2024) · Social Science Computer Review · doi:10.1177/08944393241270382 · Cited by 9
“Prior research has highlighted a trend in which approximately 9 – 15% of active accounts on social media platforms are, in fact, automated bots (Varol et al., 2017).”
Digital activism and public opinion: understanding the role of social media during the Gaza Conflict
Mohammed, A. B., Al‐Okaily, M., Qasim, D., et al. (2025) · Journal of Islamic marketing · doi:10.1108/jima-03-2024-0101 · Cited by 9
Shajari, S., & Agarwal, N. (2025) · Social Network Analysis and Mining · doi:10.1007/s13278-025-01470-7 · Cited by 10
“Another study by Varol et al. (2017) developed machine learning-based classifiers to distinguish between human and automated accounts, offering insights into the behaviors and network structures of bots.”
Facebook fake profile identification: technical and ethical considerations
Pourghomi, P., Dordevic, M., & Safieddine, F. (2020) · International Journal of Pervasive Computing and Communications · doi:10.1108/ijpcc-06-2019-0049 · Cited by 4
Combating disinformation with AI: Epistemic and ethical challenges
Lange, B., & Lechterman, T. M. (2021) · IEEE International Symposium on Technology and Society (ISTAS) · doi:10.1109/istas52410.2021.9629122 · Cited by 9
Characterizing User Susceptibility to COVID-19 Misinformation on Twitter
Teng, X., Lin, Y., Chung, W., Li, A., & Kovashka, A. (2022) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v16i1.19353 · Cited by 12
“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.”
BackgroundMethodInfluentialWang, R., Walter, D., & Ophir, Y. (2023) · Social Science Computer Review · doi:10.1177/08944393231188472 · Cited by 9
“In recent years, researchers have warned of an increase in the number of bots operating on social media, with some estimating that 9% – 15% of all Twitter accounts, for example, were bots (Varol et al., 2017).”
BackgroundThe anatomy of conspiracy theorists: Unveiling traits using a comprehensive Twitter dataset
Gambini, M., Tardelli, S., & Tesconi, M. (2024) · Computer Communications · doi:10.1016/j.comcom.2024.01.027 · Cited by 9
Do You Really Follow Them? Automatic Detection of Credulous Twitter Users
Balestrucci, A., Nicola, R. D., Petrocchi, M., & Trubiani, C. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-33607-3_44 · Cited by 10
“We consider three publicly available datasets: CR15 [10], CR17 [12], and VR17 [26].”
BackgroundMethodInfluentialQuality Indicators for Social Business Intelligence
Berlanga, R., Lanza-Cruz, I., & Aramburu, M. J. (2019) · International Conference on Social Networks Analysis, Management and Security (SNAMS) · doi:10.1109/snams.2019.8931862 · Cited by 9
“Other applications aimed at the detection of spammers, bots and advertising campaigns, have proposed intelligent analysis techniques for social metrics [30] [31] [32].”
BackgroundAn Analysis of the Characteristics of Verified Twitter Users
Kabakuş, A. T., & Şimşek, M. (2019) · Sakarya University Journal of Computer and Information Sciences · doi:10.35377/saucis.02.03.649708 · Cited by 9
“It is reported that there are a large number of fake/spam accounts [10], [11] despite the serious actions that have already been proposed by Twitter [12].”
BackgroundLook who’s talking now: Cancer in primary care on Twitter. An observational study
Milley, K. M., Chima, S., Cummings, K.-L., & Emery, J. D. (2020) · BJGP Open · doi:10.3399/bjgpopen20x101134 · Cited by 9
Task-agnostic representation learning of multimodal twitter data for downstream applications
Rivas, R., Paul, S., Hristidis, V., Papalexakis, E. E., & Roy–Chowdhury, A. K. (2022) · Journal Of Big Data · doi:10.1186/s40537-022-00570-x · Cited by 9
“In the dataset described in “Dataset”, bots may be underrepresented compared to the bot detection data because bots are estimated to make up only 9–15% of active Twitter accounts [67].”
BackgroundA hybrid framework for bot detection on twitter: Fusing digital DNA with BERT
Chawla, V., & Kapoor, Y. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14730-5 · Cited by 10
“Bot accounts have also been leveraged to promote extremism by adopting terrorism ideologies [12, 32, 46, 65, 89].”
BackgroundIdentifying Coordinated Accounts in Disinformation CampaignsPreprint
Sharma, K., Ferrara, E., & Liu, Y. (2020) · arXiv (Cornell University) · Cited by 8
Self-citationYu, M., Cheng, Y., & Shi, C. (2023) · Applied Sciences · doi:10.3390/app13169464 · Cited by 11
Twitter bots, democratic deliberation and social accountability: the case of #OccupyWallStreet
Neu, D., & Saxton, G. D. (2023) · Accounting Auditing & Accountability Journal · doi:10.1108/aaaj-01-2023-6234 · Cited by 9
Fine-Grained Anomaly Detection on Dynamic Graphs via Attention Alignment
Chen, D., Zhao, X. H., & Xiao, W. (2024) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde60146.2024.00246 · Cited by 9
“These malicious users propagate a series of detrimental behaviors, including spam, disinformation, and other illicit activities [5].”
BackgroundAlsodi, O., Zhou, X., Gururajan, R., Shrestha, A., & Btoush, E. (2025) · Applied Sciences · doi:10.3390/app15073898 · Cited by 14
Wang, X., Tang, H., Zheng, K., & Tao, Y. (2020) · IET Information Security · doi:10.1049/iet-ifs.2018.5286 · Cited by 8
“[35], which contained filtered data from ∼10% of the public tweets of Twitter that had been monitored from November 2015 to January 2016.”
BackgroundMachine Learning-Based malicious users’ detection in the VKontakte social network
SAMOKHVALOV, D. I. (2020) · Proceedings of the Institute for System Programming of RAS · doi:10.15514/ispras-2020-32(3)-10 · Cited by 8
“In [25] a framework for extracting a large collections of Twitter accounts was proposed.”
BackgroundMachine Learning Algorithms for Detecting and Analyzing Social Bots Using a Novel Dataset
Jalal, N., & Ghafoor, K. Z. (2022) · ARO-The Scientific Journal of Koya University · doi:10.14500/aro.101032 · Cited by 11
“The social bot impact is so significant that some reports indicate that 9–15% of the active accounts on Twitter are social bots (Varol, et al., 2017).”
BackgroundMarín-Albaladejo, J. A. (2023) · Espejo de Monografías de Comunicación Social · doi:10.52495/c3.emcs.10.p96 · Cited by 11
Finding Organizational Accounts Based on Structural and Behavioral Factors on Twitter
Alzahrani, S., Gore, C. C., Salehi, A., & Davulcu, H. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-93372-6_18 · Cited by 7
“[12] works on resolving a botdetection issue by employing a diverse set of features categorized into user profile, followers, network, temporal, content and sentiment related ones.”
BackgroundHow Humans Versus Bots React to Deceptive and Trusted News Sources: A Case Study of Active Users
Glenski, M., Weninger, T., & Volkova, S. (2018) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1109/asonam.2018.8508700 · Cited by 8
“5 percent of its active monthly users were automated accounts1 and subsequent studies found this to be a low estimate of the actual prevalence of bot accounts [1], [20].”
BackgroundDoes Twitter language reliably predict heart disease? A commentary on Eichstaedt et al. (2015a)
Brown, N. J. L., & Coyne, J. C. (2018) · PeerJ · doi:10.7717/peerj.5656 · Cited by 8
“(2017) warned that bots, or humans tweeting like bots, represent a considerable challenge to the interpretability of Twitter data; this theme has become particularly salient in view of recent claims that a substantial proportion of the content on Twitter and other social media platforms may not represent the spontaneo…”
BackgroundFagbola, T. M., & Colin, S. (2019) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2019.0101047 · Cited by 8
“org pollute the content, manipulate and influence public sentiment in online social networks and performing human-associated activities like tweeting, retweeting and liking among others [21-22].”
BackgroundDiscovery and Classification of Twitter Bots
Shevtsov, A., Oikonomidou, M., Antonakaki, D., Pratikakis, P., Kanterakis, A., Fragopoulou, P., & Ioannidis, S. (2022) · SN Computer Science · doi:10.1007/s42979-022-01154-5 · Cited by 7
Scarborough, W. J., & Helmuth, A. S. (2021) · Sociological Forum · doi:10.1111/socf.12686 · Cited by 8
Forsage: Anatomy of a Smart-Contract Pyramid Scheme
Kell, T., Yousaf, H., Allen, S., Meiklejohn, S., & Juels, A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-47751-5_14 · Cited by 10
“For comparison, in March of 2017, Varol et al. [35] used an earlier version of the Botometer tool to perform a measurement study across all of Twitter and found that “between 9 and 15% of active Twitter accounts are bots.”
Method1. IS THE FIRST AMENDMENT OBSOLETE?
Wu, T. (2019) · Columbia University Press eBooks · doi:10.7312/poze19712-002 · Cited by 8
Uyheng, J., & Carley, K. M. (2021) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v15i1.18098 · Cited by 9
“…in this area from the Asia-Pacific thus offers commensurate knowledge with much of the existing work in the West (Luceri, Giordano, and Ferrara 2020; Varol et al. 2017), while recognizing further work needs to be done to address gaps in dominant methodologies to keep up with paradigm shifts in…”
BackgroundBayesian identification of bots using temporal analysis of tweet storms
Kirn, S. L., & Hinders, M. K. (2021) · Social Network Analysis and Mining · doi:10.1007/s13278-021-00783-7 · Cited by 7
Malicious accounts detection from online social networks: a systematic review of literature
Sassi, I. B., & Yahia, S. B. (2021) · International Journal of General Systems · doi:10.1080/03081079.2021.1976773 · Cited by 8
“The authors in Varol et al. (2017) have also applied the K-Means algorithm to gather bot accounts into behavioral clusters.”
BackgroundMethodInfluentialData Curation Implications of Qualitative Data Reuse and Big Social Research
Mannheimer, S. (2021) · Journal of eScience Librarianship · doi:10.7191/jeslib.2021.1218 · Cited by 10
“Multiple accounts from one user, fake accounts, and bots can all introduce errors, bias, and distortion (Marwick and Boyd 2011; Shah, Cappella, and Neuman 2015; Varol et al. 2017).”
BackgroundBreuer, A., Tehrani, N. K., Tingley, M., & Cottel, B. (2023) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3580305.3599471 · Cited by 8
“Whereas traditional PA models capture how new users tend to seek out already-popular users, 𝑘 CDPA captures how new users tend to seek out (request and/or be requested by) users who are already popular with those of the new user’s fake/real class: • New users’ outgoing friend requests: We model…”
BackgroundMethodEvolving Bots: The New Generation of Comment Bots and their Underlying Scam Campaigns in YouTube
Na, S. H., Cho, S., & Shin, S. (2023) · ACM Internet Measurement Conference (IMC) · doi:10.1145/3618257.3624822 · Cited by 11
“Given the severity of social bots, many studies were conducted to understand social bot behavior [26, 32, 38] and propose detection methods of these automated entities [9, 12, 19].”
BackgroundAnalyzing Social and Communication Network Structures of Social Bots and Humans
Khaund, T., Bandeli, K. K., Hussain, M. N., Obadimu, A., Al-khateeb, S., & Agarwal, N. (2018) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1109/asonam.2018.8508665 · Cited by 8
“Researchers in [8] identified predictive features such as invitation frequency, outgoing requests accepted, and network clustering coefficient and utilized network-based techniques, crowdsourcing strategies, feature-based supervised learning, and hybrid systems to detect bots to detect bots and developed a tool called…”
BackgroundNetwork Model for Online News Media Landscape in Twitter
Gaol, F. L., Matsuo, T., & Maulana, A. (2019) · Information · doi:10.3390/info10090277 · Cited by 8
“It is known that about 15% of Twitter accounts are bot accounts that are controlled by software [39].”
BackgroundTwitter Discourses on Climate Change: Exploring Topics and the Presence of BotsPreprint
Marlow, T., Miller, S., & Roberts, J. T. (2020) · doi:10.31235/osf.io/h6ktm · Cited by 7
Alothali, E., Hayawi, K., & Alashwal, H. (2023) · Applied Sciences · doi:10.3390/app13074443 · Cited by 7
Cooperative bots exhibit nuanced effects on cooperation across strategic frameworks
Si, Z., He, Z., Shen, C., & Tanimoto, J. (2025) · Journal of The Royal Society Interface · doi:10.1098/rsif.2024.0427 · Cited by 9
“However, with the advancement of artificial intelligence (AI), humans are increasingly interacting with social bots in various realms [11–13].”
Multi-stage self-training social bot detection based on graph neural network
Wang, K., Wang, X., Chen, K., Wang, Z., & Zheng, K. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110816 · Cited by 8
BotSSCL: Social Bot Detection with Self-Supervised Contrastive Learning
Akhtar, M. M., Bhuiyan, N. S., Masood, R., Ikram, M., & Kanhere, S. S. (2025) · Online Social Networks and Media · doi:10.1016/j.osnem.2025.100318 · Cited by 14
A Propaganda Desinformativa no Projeto de Destruição Nacional Bolsonarista
Regattieri, L. L. (2023) · Revista ECO-Pós · doi:10.29146/eco-ps.v26i01.28005 · Cited by 8
Patterns of human and bots behaviour on Twitter conversations about sustainability
Mouronte-López, M. L., Sánchez-Seco, J. G., & Benito, R. M. (2024) · Scientific Reports · doi:10.1038/s41598-024-52471-z · Cited by 7
First public dataset to study 2023 Turkish general election
Najafi, A., Muğurtay, N., Zouzou, Y., et al. (2024) · Scientific Reports · doi:10.1038/s41598-024-58006-w · Cited by 7
Self-citationInvestigation of Emotion Exchange Motifs in Bot/Human Interactions During Riot Events
Kušen, E., & Strembeck, M. (2018) · International Conference on Social Networks Analysis, Management and Security (SNAMS) · doi:10.1109/snams.2018.8554860 · Cited by 7
“Following the procedure proposed in [30], we classified accounts as bots if the bot likelihood score assigned by Botometer was larger than 0.”
MethodTDM: A Tensor Data Model for Logical Data Independence in Polystore Systems
Leclercq, É., & Savonnet, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-14177-6_4 · Cited by 7
“It uses 1,150 criteria and machine learning techniques to calculate the probability [51].”
MethodDİJİTALLEŞEN SİYASAL İLETİŞİMDE BİLİŞİMSEL PROPAGANDA: BOTLAR
YETKİN, B. (2019) · Atatürk İletişim Dergisi · doi:10.32952/atauniiletisim.486854 · Cited by 7
Characterizing reticulation in online social networks during disasters
Fan, C. H., Shen, J., Mostafavi, A., & Hu, X. (2020) · Applied Network Science · doi:10.1007/s41109-020-00271-5 · Cited by 6
“%) in existing studies (Varol et al. 2017).”
BackgroundMake a Difference in a Different Way: Twitter Bot Creators and Wikipedia Transparency.
Livingstone, R. M. (2021) · Computer Supported Cooperative Work (CSCW) · doi:10.1007/s10606-021-09411-6 · Cited by 7
“…was inspired by the work of journalist Kelly Weill, who identi fi ed the relevant IP ranges and wrote about historical anonymous edits to Wikipedia articles ‘ for several well-known victims of police altercations, including entries for Eric Garner, Sean Bell, and Amadou Diallo ’ (Weill 2015).”
MethodNikulchev, E. V., Gusev, A., Ilin, D., et al. (2021) · Applied Sciences · doi:10.3390/app112211034 · Cited by 7
Wright, J. M., Kelly-Thompson, K., Weldon, S. L., Goldwasser, D., Einwohner, R. L., Sinclair‐Chapman, V., & Tormos‐Aponte, F. (2022) · Contention · doi:10.3167/cont.2022.100203 · Cited by 8
A Method of Machine Learning for Social Bot Detection Combined with Sentiment Analysis
Long, G., Lin, D., Lei, J., Zhi-yong, G., Hu, Y., & Xia, L. (2022) · International Conference on Machine Learning and Natural Language Processing (MLNLP) · doi:10.1145/3578741.3578790 · Cited by 8
“The challenge of malicious social bot detection is gradually increasing, but most of the detection technologies so far only stay at the account level; their social bot detection methods were to extract features from the metadata of accounts, and were detected through supervised learning [14, 15].”
BackgroundMethodThe role of hyperactive Twitter accounts in the diffusion of political information
Matuszewski, P., & Szabó, G. (2023) · Policy Studies · doi:10.1080/01442872.2023.2237911 · Cited by 7
“Such accounts are run by humans who also use automated programs to post tweets or interact with content during their absence (Chu et al. 2012; Varol et al. 2017).”
CALEB: A Conditional Adversarial Learning Framework to enhance bot detection
Dimitriadis, I., Dialektakis, G., & Vakali, A. I. (2023) · Data & Knowledge Engineering · doi:10.1016/j.datak.2023.102245 · Cited by 15
CLASSIFYING TWITTER USER AS A BOT OR NOT AND COMPARING DIFFERENT CLASSIFICATION ALGORITHMS.
Haidermota, M. (2018) · International Journal of Advanced Research in Computer Science · doi:10.26483/ijarcs.v9i3.5949 · Cited by 7
“The best classification performance of 0.95 AUC is obtained by the Random Forest model [3].”
MethodInfluentialCharacterizing Politically Engaged Users' Behavior During the 2016 US Presidential Campaign
Caetano, J. A., Almeida, J. M., & Marques-Neto, H. T. (2018) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1109/asonam.2018.8508459 · Cited by 7
“This tool combines machine learning algorithms, sentiment analysis, and other features to define whether a given profile has more characteristics of being legitimate or being a false account [12].”
BackgroundMethodInfluentialSocial Network Polluting Contents Detection through Deep Learning Techniques
Martinelli, F., Mercaldo, F., & Santone, A. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8852080 · Cited by 8
“It is estimated that 9-15% of active Twitter accounts may be social bots [20] and that 15% of the total Twitter population active in the US Presidential election discussion were bots.”
BackgroundCharacterizing the language-production dynamics of social media users
Stine, Z. K., & Agarwal, N. (2019) · Social Network Analysis and Mining · doi:10.1007/s13278-019-0605-7 · Cited by 7
“In response to the growing importance of social media, much research has been focused on discriminating between genuine, good-faith social media users, and bad-faith users, often in the form of automatically operated accounts colloquially referred to as bots (Ferrara et al. 2016; Cresci et al. 2017, 2018; Varol et al.…”
Detecting Malicious Social Robots with Generative Adversarial Networks
Wu, B., Liu, L., Dai, Z., Wang, X., & Zheng, K. (2019) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2019.11.018 · Cited by 7
“Varol and Ferrara [4] extracted 1150 features from public data and metadata regarding users, friends, tweet content and sentiments, network patterns, and activity time series and used random forest, AdaBoost, logistic regression, and decision tree classifiers to detect social robots.”
BackgroundMethodGuiding the Students in High School by Using Machine Learning
Ababneh, M. A.-K., Aljarrah, A., Karagözlü, D., & Özdamlı, F. (2021) · TEM Journal · doi:10.18421/tem101-48 · Cited by 7
Not All the Bots Are Created Equal: The Ordering Turing Test for the Labeling of Bots in MMORPGs
Paoli, S. D. (2017) · Social Media + Society · doi:10.1177/2056305117741851 · Cited by 7
Sneak into Devil's Colony- A study of Fake Profiles in Online Social Networks and the Cyber LawPreprint
Wani, M. A., Jabin, S., Yazdani, G., & Ahmad, N. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.08810 · Cited by 7
“The authors in [99] have deeply studied the behavior of bot-controlled Twitter accounts and highlighted how bots use different retweet and mentioned strategies while interacting with humans or other bots on the network and presented a framework to detect such accounts.”
BackgroundAdvanced Algorithmic Approaches for Scam Profile Detection on Instagram
Bokolo, B. G., & Liu, Q. (2024) · Electronics · doi:10.3390/electronics13081571 · Cited by 6
Zhou, J., Zhang, D., Zhu, J., Wang, F., & Bi, C. (2025) · Information · doi:10.3390/info16100850 · Cited by 7
Few voices, strong echo: Measuring follower homogeneity of politicians’ Twitter accounts
Rusche, F. (2024) · New Media & Society · doi:10.1177/14614448221099860 · Cited by 6
Koontz, N. A., Tomblinson, C. M., Shatzkes, D. R., Glastonbury, C. M., Phillips, C. D., Dean, K. E., Strauß, S., Agarwal, M., Robson, C. D., & Wiggins, R. H. (2022) · American Journal of Neuroradiology · doi:10.3174/ajnr.a7711 · Cited by 6
On Using Node Indices and Their Correlations for Fake Account Detection
Asghari, S., Chehreghani, M. H., & Chehreghani, M. H. (2022) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata55660.2022.10020627 · Cited by 7
Bots Versus Humans: Discursive Activism During the Pandemic in the Iranian Twittersphere
Kermani, H., Makou, A. B., Tafreshi, A., Ghodsi, A. M., & Ataee, H. (2023) · Social Media + Society · doi:10.1177/20563051231216927 · Cited by 8
“These bots are prevalent across various social media platforms, particularly Twitter, where studies suggest that approximately 15% of accounts operate automatically or semi-automatically (Varol et al., 2017).”
BackgroundUnveiling the Veiled Threat: The Impact of Bots on COVID-19 Health Communication
Ünlü, A., Truong, S., Sawhney, N., & Tammi, T. (2024) · Social Science Computer Review · doi:10.1177/08944393241275641 · Cited by 8
“In benchmark studies, the percentage of bot accounts ranges from 9% to 15% of total accounts on Twitter (Suarez-Lledo & Alvarez-Galvez, 2022; Varol et al., 2017).”
Leclercq, É., Gillet, A., Grison, T., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-662-60531-8_3 · Cited by 6
A ROOM WITH A VUI – VOICE USER INTERFACES IN THE TESOL CLASSROOM
Kent, D. (2020) · Teaching English With Technology · Cited by 6
Misinformation, Fake News and Rumor Detection
Arora, N. (2021) · Smart innovation, systems and technologies · doi:10.1007/978-981-16-3398-0_14 · Cited by 7
Kwon, K. H., Lee, M. H., Han, S. P., & Park, S. (2022) · New Media & Society · doi:10.1177/14614448221099170 · Cited by 7
“Substantial academic effort has been put into the detection of fake accounts (e.g. Davis et al., 2016; Varol et al., 2017; Williamson and Scrofani, 2019) and false information diffusion (e.g. Bastos and Mercea, 2019; Grinberg et al., 2019; Shin et al., 2017; Vosoughi et al., 2018) by analyzing…”
BackgroundOpinion Dynamics: Bots and the Spiral of Silence
Shukla, A., Sahasrabudhe, N., & Moharir, S. (2023) · International Conference on Communication Systems & Networks (COMSNETS) · doi:10.1109/comsnets56262.2023.10041283 · Cited by 6
“…on popular social media platforms has motivated numerous studies examining various aspects including the number of bots on various social networks [6], the fraction of overall activity that includes bots [7], identifying bots on social networks [8], and identifying and classifying the various…”
BackgroundHarnessing Machine Learning to Unveil Emotional Responses to Hateful Content on Social Media
Louati, A., Louati, H., Albanyan, A., Lahyani, R., Kariri, E., & Alabduljabbar, A. (2024) · Computers · doi:10.3390/computers13050114 · Cited by 7
Analysis of Arabic Bot Behaviors
Boreggah, B., Al-Razooq, A., Al‐Razgan, M., & AlShabib, H. (2018) · Saudi Computer Society National Computer Conference (NCC) · doi:10.1109/ncg.2018.8592980 · Cited by 6
“Another bot detection framework, and one of the most famous on the field, is BotOrNot now called Botometer [6][7].”
BackgroundDistorting Political Communication: The Effect Of Hyperactive Users In Online Social Networks
Papakyriakopoulos, O., Shahrezaye, M., Serrano, J. C. M., & Hegelich, S. (2019) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infcomw.2019.8845094 · Cited by 7
“We focused on Facebook, because the platform’s api restrictions and its monitoring system largely prevent automated activities, as e.g. performed by social bots on other platforms [22], [23].”
BackgroundCharacterizing Man-made vs. Machine-made Chatbot Dialogs
Uchendu, A., Cao, J., Wang, Q., et al. (2019) · doi:10.36370/tto.2019.27 · Cited by 6
“Recently, some Tweets have been found to be generated by chatbots which are known as social bots (i.e chatbots that are accounts controlled by software; algorithmically generating content and establishing interactions) (Varol et al., 2017).”
BackgroundMethodInfluentialEmotions through texts and images
Bouko, C. (2020) · Pragmatics Quarterly Publication of the International Pragmatics Association (IPrA) · doi:10.1075/prag.18060.bou · Cited by 6
Social Media, Democracy and Fake News in Pakistan: An Analysis
Warrich, H. U. R., Hussain, S., & Durreshehwar (2020) · Global Political Review · doi:10.31703/gpr.2020(v-i).10 · Cited by 6
“Political communication researchers like Gentzkow (2017) and Faris (2017) in their detailed studies have shown that despite presence of huge amount of quality information on the social media, fake industry has successfully penetrated the public domains.”
BackgroundStrategic Information Operation in YouTube: The Case of the White Helmets
Choudhury, N., Ng, K. W., & Iamnitchi, A. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-61255-9_31 · Cited by 7
A Board Game to Fight Against Misinformation and Fake News
Maze, C., Haye, A., Sarre, J., Galaup, M., Lagarrigue, P., & Lelardeux, C. P. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-63464-3_31 · Cited by 6
Searching for Unknown Unknowns: Unsupervised Bot Detection to Defeat an Adaptive Adversary
Chew, P. A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-93372-6_39 · Cited by 6
Duplicity in Alternative Marketing Communications
Nistor, C., Yalcin, T., & Pehlivan, E. (2018) · Markets Globalization & Development Review · doi:10.23860/mgdr-2018-03-02-04 · Cited by 7
“By some estimates, 9 to 15% of active Twitter accounts are bots (Varol et al. 2017).”
BackgroundBot Detection: Will Focusing on Recall Cause Overall Performance Deterioration?
Nazer, T. H., Davis, M., Karami, M., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-21741-9_5 · Cited by 6
“Words, phrases [16], and topics [11] of social media posts can be a strong indicator of bot activity.”
BackgroundMethodInfluential
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
