BotOrNot: A System to Evaluate Social Bots

By Clayton A. Davis, Onur Varol, Emilio Ferrara, Alessandro Flammini, Filippo Menczer. The Web Conference, 2016

923 citations recorded by the source corpus.

While most online social media accounts are controlled by humans, these platforms also host automated agents called social bots or sybil accounts. Recent literature reported on cases of social bots imitating humans to manipulate discussions, alter the popularity of users, pollute content and spread misinformation, and even perform terrorist propaganda and recruitment actions. Here we present BotOrNot, a publicly-available service that leverages more than one thousand features to evaluate the extent to which a Twitter account exhibits similarity to the known characteristics of social bots. Since its release in May 2014, BotOrNot has served over one million requests via our website and APIs.

Subfields: Information Systems, Sociology and Political Science, Signal Processing

View Paper: https://www.semanticscholar.org/paper/2913fcbb96206a2ca2de94f17a4769dba133a99a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Sociology and Political Science

In Signal Processing

Citations in the corpus

Online Human-Bot Interactions: Detection, Estimation, and Characterization (2017, methodology): “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).”
Finding and Characterizing Information Warfare Campaigns (2020, methodology): “The Botometer Application Programming Interface (API) accepts a user ID or screen names as input, scrapes the Twitter API using the consumer provided keys on the server side, and then returns a score for content, friends, network, sentiment, temporal, user, and the universal score for the account.”
FakeNewsNet: A Data Repository with News Content, Social Context and Dynamic Information for Studying Fake News on Social Media (2018, methodology): “We set the threshold of 0.5 on the bot score returned from the Botometer results to determine bot accounts.”
The Paradigm-Shift of Social Spambots: Evidence, Theories, and Tools for the Arms Race (2017, background): “BotOrNot? is a publiclyavailable service(7) to evaluate the similarity of a Twitter account with the known characteristics of social spambots [14].”
Arming the public with artificial intelligence to counter social bots (2019, methodology): “Botometer is based on a supervised machine learning approach (Davis et al., 2016; Varol et al., 2017a).”
Darling or Babygirl ? Investigating Stylistic Bias in Sentiment Analysis (2018, methodology): “To reduce the probability that a user was a bot, we screened each through the Botometer API (Davis et al., 2016) and remove those with a bot likelihood score of .8 or higher, removing fewer than 1%.”
The spread of true and false news online (2018, methodology): “[55] to remove all accounts that were identified as bots.”
Disinformation and social bot operations in the run up to the 2017 French presidential election (2017, methodology): “Botometer has been proven quite accurate in detecting social bots (Davis, et al., 2016; Varol, et al., 2017), However, the public interface of Botometer has two limitations that prevented us to use it in this project: the framework relies on the Twitter API to collect recent data about the accounts…”
An exploratory study of COVID-19 misinformation on Twitter (2020, positive): “To analyse the role of bots, we examined each account by using a bot detection API [67].”
Contrast Pattern-Based Classification for Bot Detection on Twitter (2019, methodology): “Bot or Not uses a Random Forest classifier [35] over 1,000 features from all the categories, obtaining a 0.95 of Area Under the ROC Curve (AUC).”
False Information on Web and Social Media: A Survey (2018, methodology): “In cases of rumors, Bessi et al. [13] studied over 20.7 million tweets related to US presidential election, and identified users involved in tweeting as bots or honest users using a classification tool produced by Davis et al. [21].”
The spread of low-credibility content by social bots (2017, positive): “The Botometer system used in this paper has been publicly available for a few years [10].”
No . 2017 . 5 Computational Propaganda in the United States of America : Manufacturing Consensus Online (2017, methodology): “First, we collected data from the Twitter streaming API.”