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 901–933 of 933
BotSphere: A Multi-agent Framework for Modeling Social Bot Influence on Public Opinion Dynamics
Yang, K., Fan, W., Lin, C., & Ye, L. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-9507-5_27
Unified network ensemble and chunk-based feature selection for improved social bot detection
Sharma, J., & Borah, S. (2026) · Knowledge and Information Systems · doi:10.1007/s10115-026-02807-0
Explainable Analysis of Fake Instagram Account Detection Using Graph and Behavioral Features
Miranda-Caramé, I., Rodríguez-Dueñas, A., Jiménez-Navarro, M. J., et al. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-29254-4_26
When AI Joins the Thread: A Computational Analysis of Gendered Human-AI Interactions on Weibo
Li, C., Wang, Z., Wang, Y., Johnson, J., De, S., & Chen, Z. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-9877-9_11
Sari, W. Y. (2026) · Priviet Social Sciences Journal · doi:10.55942/pssj.v6i6.2023
“…should not be treated as equivalent to national public opinion because platform users are not demographically representative, and discourse may be shaped by media accounts, campaign narratives, automated activity, or coordinated posting behavior (Ferrara, 2023; Varol et al., 2017; Verma, 2022).”
Detecção de Bots Baseada em Caracterização de Dados
Chissingui, H. J. (2026) · Revista Angolana de Ciencias · doi:10.54580/r0801.14
POPÜLİZM ÇAĞINDA DİJİTAL ÖZNELERİN İNŞASI: TRUTH SOCIAL ÖRNEĞİ
Konukcu, Y. (2026) · Nişantaşı üniversitesi sosyal bilimler dergisi/Nişantaşı Üniversitesi sosyal bilimler dergisi · doi:10.52122/nisantasisbd.1909880
Jain, A., Jaulkar, P., Agrawal, A., Garvin, F., & Khobragade, R. H. (2026) · Cureus Journal of Computer Science. · doi:10.7759/s44389-026-00148-1
RB-GNN: Securing Social Collaboration via Residual Behavior Graph Learning
Wang, Z., Ji, L., & Liu, S. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11581654
“Early detection approaches primarily relied on feature engineering, extracting cues from user profiles (e.g., account † Corresponding author: Shuxin Liu (liusxndsc@163.com). age) and content (e.g., linguistic patterns) [4].”
Masoudnia, H., Esfahani, A. S., Forghani, M., Moghimi, M., & Esfahany, H. S. (2026) · Social Science Computer Review · doi:10.1177/08944393261460815
BotCHF: camouflage-heterogeneity-aware fusion for social bot detection
Wang, X., Shi, S., Qiao, K., Hu, H., Liu, Z., Zhang, Y., Han, J., & Yan, B. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-01013-w
Tao, S., Zhao, Y., & Hong, T. (2026) · Systems · doi:10.3390/systems14070817
An Explainable AI-based XGBoost Model for Spambot Detection Across Multiple Social Media Platforms
Dhanni, C., & Pallavi, K. V. (2026) · doi:10.1109/icdca69396.2026.11620085
“This helped to set the extent of the problem and show that account metadata could be used as a means of detection [4].”
OTPCL: Optimal Transport Driven Pseudo-Labeling with Contrastive Learning for Social Bot Detection
Xu, R., Hu, M., Yang, X., Jiang, M., Wang, Z., Gao, H., & Cheng, R. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818069
“Prior studies show that automated accounts can spread low-credibility content more widely and accelerate its circulation on social media, distorting the information that users encounter at a large scale [14, 33, 35, 38, 40].”
InfluentialThe reciprocity gap: How autonomous AI agent networks challenge platform ecosystem design
Pérez, C., & Sokolova, K. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.105084
Zhang, L., & Cummings, J. J. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2707670
An Ethical and Emotionally Intelligent Social Media Plugin Using Responsible & Explainable AI
Wickremasinghe, N. S., Ullandupitiya, U. P. L. I., Jayawardena, D. S., Jayanetti, J. K. D. D. T., Rathnayake, S. J., & Nawarathne, M. (2026) · International Conference on Emerging Smart Technologies and Applications (eSmarTA) · doi:10.1109/esmarta70636.2026.11652165
“Social bot detection has advanced from features and behavioral patterns to deep learning and generalization-based methods [2], [17].”
InfluentialSana, Rehman, S. U., Mahmood, K., & Ali, I. (2026) · Journal of Information Science · doi:10.1177/01655515261471855
MC-FF: A multi-community feature fusion framework for social bot detection
Li, W., Deng, J., You, J., et al. (2026) · Computers & Security · doi:10.1016/j.cose.2026.105121
Haile, Y. A. (2026) · Media War & Conflict · doi:10.1177/17506352261477304
Social Media Data Toolkit: Standardization and pseudonymization of social network datasets
Najafi, A., Iannucci, L., Kivelä, M., & Varol, O. (2026) · Online Social Networks and Media · doi:10.1016/j.osnem.2026.100356
Self-citationMohanty, A., Anjum, G. A., Parappurath, J. M., Kishore, J., & Dushyantha, N. D. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-33581-4_15
A Review of Models and Methods for Assessing Social Media User Influence
Zhang, Z. (2026) · International Conference on Digital Society and Artificial Intelligence (DSAI) · doi:10.1145/3833541.3833542
Mahesh Sankar, S., Renjith, M., R, S. N. M., & Sreenivasan, A. (2026) · International Conference on Inventive Systems and Control (ICISC) · doi:10.1109/icisc69558.2026.11681691
A Data-Driven Multidimensional Comparison of LLM-Driven Social Robots on Weibo
Deng, J., Chen, J., Pan, Y., & Xin, Z. (2026) · International Conference on Big Data and Information Analytics (BigDIA) · doi:10.1109/bigdia71496.2026.11684705
“Early studies mainly investigated their roles in information diffusion, political communication, crisis response, and bot detection [9]–[12].”
Pham, K. N., Tran, N. T. V., Nguyen, T. Q., et al. (2026) · International Conference on Multimedia Analysis and Pattern Recognition (MAPR) · doi:10.1109/mapr72750.2026.11685731
“Early bot detection methods rely on feature engineering, extracting handcrafted features from user metadata and tweet content [4], [12].”
Nabil, M. A., Akand, A. R., Datta, A., et al. (2026) · doi:10.1109/iccvbic71195.2026.11689534
“Cai et al. [12] made a comparison between the behavioral differences of bot and human users, and Varol et al. [13] analyzed the online interaction between humans and bots through a large-scale Twitter characteristics analysis.”
Zhao, Z., He, Y., & Wang, H. (2026) · Online Media and Global Communication · doi:10.1515/omgc-2025-0049
“Botometer has been extensively applied in prior studies on political communication and social bot activity, demonstrating its reliability and validity across diverse research contexts (Ferrara 2017; Varol et al. 2017).”
InfluentialŞimşek, S. S. (2026) · Liberal Düşünce Dergisi · doi:10.36484/liberal.1865529
Erazo, J. L. S., & Cruz‐Cárdenas, J. (2026) · Informatics · doi:10.3390/informatics13100156
Guo, S., & Zhou, Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-68571-x
“Botometer and its variants 23 consolidated more than a thousand features—spanning account metadata, temporal activity patterns, network statistics, content, and sentiment—into a random-forest classifier that set a long-standing baseline on Twitter.”
Group Dynamics Within Online Communities
Debb, S. M. (2026) · Springer eBooks · doi:10.1007/978-3-031-52643-5_312-1
Campaign-Level Behavioral Archetypes Transfer Across Political Campaigns
Amure, R., & Agarwal, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-40581-4_22
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
