Detection and visualization of misleading content on Twitter

Abstract

The problems of online misinformation and fake news have gained increasing prominence in an age where user-generated content and social media platforms are key forces in the shaping and diffusion of news stories. Unreliable information and misleading content are often posted and widely disseminated through popular social media platforms such as Twitter and Facebook. As a result, journalists and editors are in need of new tools that can help them speed up the verification process for content that is sourced from social media. Motivated by this need, in this paper we present a system that supports the automatic classification of multimedia Twitter posts into credible or misleading. The system leverages credibility-oriented features extracted from the tweet and the user who published it, and trains a two-step classification model based on a novel semisupervised learning scheme. The latter uses the agreement between two independent pre-trained models on new posts as guiding signals for retraining the classification model. We analyze a large labeled dataset of tweets that shared debunked fake and confirmed real images and videos, and show that integrating the newly proposed features, and making use of bagging in the initial classifiers and of the semi-supervised learning scheme, significantly improves classification accuracy. Moreover, we present a web-based application for visualizing and communicating the classification results to end users.

A unified approach for detection of Clickbait videos on YouTube using cognitive evidences

“…They have also created the FVC-2018 dataset to train and evaluate the proposed method. In the verification algorithm, the author applied the same process that was used in [ 5 ], along with it two model variants: a concatenation of the two feature sets(videos metadata and comments feature) and the agreement-based approach given in [ 43 ] was used. Their proposed algorithm has been evaluated using 10-fold cross-validation on the dataset proposed by Papadopoulos [ 5 ].…”

“…Whereas, the second feature is based on the comments by incorporating a two-level approach. In the first level, features are extracted from the individual comment, later the credibility of each comment is evaluated independently using a pre-trained model proposed by the authors of [ 43 ]. These two sets of features are used to train the support vector machine classifier.…”

Verification of Web Videos Through Analysis of Their Online Context

“…1.4, a number of such typical text-based features are presented and categorised in five main groups. A typical case is the work of Boididou et al [4] where text-based features are used to classify a tweet as "fake" or "real", and show promising results by experimenting with supervised and semi-supervised learning approaches. The approach of Gupta et al [20] deals with 14 news events from 2011 that propagated through Twitter, and extracts "content-based" (e.g.…”

“…The approach is evaluated using RankSVM and a relevance feedback approach, showcasing that both groups of features are important for assessing tweet credibility. A comparison of the top performing approaches of the "Verifying Multimedia Use" benchmark task, which took place in MediaEval 2015 [2] and 2016 [3], is presented by Boididou et al [4] showing promising results in the challenge of automatic classification of multimedia Twitter posts into credible or misleading. The work of Wang et.…”

“…1.14). The tweet IDs can be useful indicators using existing online tools for tweet verification, such as the Tweet Verification Assistant [4]. The Tweet Verification Assistant provides a User Interface 29 that takes a single tweet as input and returns an estimate of the probability that the information contained within the tweet and any associated media (images, videos) is real.…”