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
Fake news on Twitter during the 2016 U.S. presidential election
Grinberg, N., Joseph, K., Friedland, L., Swire-Thompson, B., & Lazer, D. (2019) · Science · doi:10.1126/science.aau2706 · Cited by 1,803
“In order to further guarantee that the sample did not include bots, we identified accounts judged by BorOrNot as bot-like (35).”
BackgroundMethodThe future of social media in marketing
Appel, G., Grewal, L., Hadi, R., & Stephen, A. T. (2020) · Journal of the Academy of Marketing Science · doi:10.1007/s11747-019-00695-1 · Cited by 1,893
“For example, experts estimate that up to 15% of active Twitter accounts are bots (Varol et al.”
BackgroundTucker, J. A., Guess, A., Barbera, P., Vaccari, C., Siegel, A., Sanovich, S., Stukal, D., & Nyhan, B. (2018) · doi:10.2139/ssrn.3144139 · Cited by 1,222
The spread of low-credibility content by social bots
Shao, C., Ciampaglia, G. L., Varol, O., Yang, K.-C., Flammini, A., & Menczer, F. (2018) · Nature Communications · doi:10.1038/s41467-018-06930-7 · Cited by 1,125
Self-citationInfluence of fake news in Twitter during the 2016 US presidential election
Bovet, A., & Makse, H. A. (2019) · CUNY Academic Works (City University of New York) · Cited by 882
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
