TweetCred: Real-Time Credibility Assessment of Content on Twitter

By Aditi Gupta, Ponnurangam Kumaraguru, Carlos Castillo, Patrick Meier. Social Informatics, 2014

397 citations recorded by the source corpus.

During sudden onset crisis events, the presence of spam, rumors and fake content on Twitter reduces the value of information contained on its messages (or "tweets"). A possible solution to this problem is to use machine learning to automatically evaluate the credibility of a tweet, i.e. whether a person would deem the tweet believable or trustworthy. This has been often framed and studied as a supervised classification problem in an off-line (post-hoc) setting. In this paper, we present a semi-supervised ranking model for scoring tweets according to their credibility. This model is used in TweetCred, a real-time system that assigns a credibility score to tweets in a user's timeline. TweetCred, available as a browser plug-in, was installed and used by 1,127 Twitter users within a span of three months. During this period, the credibility score for about 5.4 million tweets was computed, allowing us to evaluate TweetCred in terms of response time, effectiveness and usability. To the best of our knowledge, this is the first research work to develop a real-time system for credibility on Twitter, and to evaluate it on a user base of this size.

Subfields: Information Systems, Sociology and Political Science, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/f2a8663d685c1fa3fa48a1d81553ea05829633f9

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 Statistical and Nonlinear Physics

Citations in the corpus

Processing Social Media Messages in Mass Emergency (2014, background): “Credible information newsworthy topics, credibility [Castillo et al. 2013]; credible topics [Canini et al. 2011]; content credibility [Gupta and Kumaraguru 2012]; users and content credibility [Gupta et al. 2014] Rumors rumor [Hughes et al. 2014b; Castillo et al. 2013]”
Hierarchical Multi-modal Contextual Attention Network for Fake News Detection (2021, methodology): “In single-modal analysis, existing methods [2, 8, 16, 27] mainly focus on extracting textual features or visual features from the text content or image information of the posts.”
Combating Fake News (2019, background): “of social media platforms include [15, 36, 69] for Twitter, [55] for Wikipedia, and [17] for click-bait websites.”
EANN: Event Adversarial Neural Networks for Multi-Modal Fake News Detection (2018, background): “Textual features are statistical or semantic features extracted from text content of posts, which have been explored in many literatures of fake news detection [4, 11, 19, 27].”
The Limitations of Stylometry for Detecting Machine-Generated Fake News (2019, background): “Another line of work for fake news detection utilizes non-textual information such as how content is propagated, by which users, its originating URL, and other metadata (Castillo, Mendoza, and Poblete 2011; Gupta et al. 2014; Zhao, Resnick, and Mei 2015; Kochkina, Liakata, and Zubiaga 2018; Liu and ”
The spread of low-credibility content by social bots (2017, neutral): “The TweetCred system [6, 18] focuses on content-based features and other kind of metadata, and distills a measure of overall information credibility.”
A survey on fake news and rumour detection techniques (2019, background): “These linguistic cues, in addition to other features, have been successfully implemented in numerous approaches concerning fake news and rumour detection [15, 38, 39, 63, 76, 78, 95, 108].”
Fake News Identification on Twitter with Hybrid CNN and RNN Models (2018, neutral): “Other works on the credibility and veracity identification on Twitter include Gupta et al that developed a framework and real-time assessment system for validating authors content on Twitter as they are being posted[20].”
Overview of the Special Issue on Trust and Veracity of Information in Social Media (2016, methodology): “Related efforts focused on devising automated methods of assessing the credibility of shared content [Gupta et al. 2014], spotting fake content [Martinez-Romo and Araujo 2013; Boididou et al. 2014], and detecting rumors spreading in social media [Qazvinian et al. 2011; Ratkiewicz et al. 2011; Seo…”
Detection and Resolution of Rumours in Social Media (2017, background): “— TweetCred 29 [Gupta and Kumaraguru 2012; Gupta et al. 2014] is a real-time, web-based system to assess credibility of content on Twitter.”