Separating Facts from Fiction: Linguistic Models to Classify Suspicious and Trusted News Posts on Twitter
Svitlana Volkova,Kyle Shaffer,Jin Yea Jang,Nathan O. Hodas +3 more
- Vol. 2, pp 647-653
TLDR
This work builds predictive models to classify 130 thousand news posts as suspicious or verified, and predict four sub-types of suspicious news – satire, hoaxes, clickbait and propaganda, and shows that neural network models trained on tweet content and social network interactions outperform lexical models.Abstract:
Pew research polls report 62 percent of U.S. adults get news on social media (Gottfried and Shearer, 2016). In a December poll, 64 percent of U.S. adults said that “made-up news” has caused a “great deal of confusion” about the facts of current events (Barthel et al., 2016). Fabricated stories in social media, ranging from deliberate propaganda to hoaxes and satire, contributes to this confusion in addition to having serious effects on global stability. In this work we build predictive models to classify 130 thousand news posts as suspicious or verified, and predict four sub-types of suspicious news – satire, hoaxes, clickbait and propaganda. We show that neural network models trained on tweet content and social network interactions outperform lexical models. Unlike previous work on deception detection, we find that adding syntax and grammar features to our models does not improve performance. Incorporating linguistic features improves classification results, however, social interaction features are most informative for finer-grained separation between four types of suspicious news posts.read more
Citations
More filters
Dissertation
MisInfoWars: A linguistic analysis of deceptive and credible news
TL;DR: This thesis will confirm that there exist sufficient textual differences between the articles of fake news and credible news to consider them distinct varieties and advocate for differentiation between disingenuous and respectable media based on linguistic variation.
Book ChapterDOI
Technological Approaches to Detecting Online Disinformation and Manipulation
TL;DR: In this article, an overview of computer-supported approaches for detecting disinformation and manipulative techniques based on several criteria is presented, focusing on the technical aspects of automatic methods which support fact checking, topic identification, text style analysis, or message filtering in social media channels.
LSACoNet: A Combination of Lexical and Conceptual Features for Analysis of Fake News Spreaders on Twitter.
TL;DR: Experimental results presented in this paper showed that a combination of representations plays an important role in identifying fake/real news spreaders.
Posted Content
FacTweet: Profiling Fake News Twitter Accounts.
TL;DR: In this article, a neural recurrent model and a variety of different semantic and stylistic features are used to detect fake news in Twitter at the account level using a CNN-based classifier.
Proceedings ArticleDOI
A Large-Scale Longitudinal Multimodal Dataset of State-Backed Information Operations on Twitter
Xiaobo Guo,Soroush Vosoughi +1 more
TL;DR: This paper proposes a large-scale and comprehensive dataset of 28 sub-datasets of state-backed tweets and accounts affiliated with 14 different countries, spanning more than 3 years, and a corresponding “negative” dataset of background tweets from the same time period and on sim- ilar topics.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings ArticleDOI
Glove: Global Vectors for Word Representation
TL;DR: A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
Proceedings ArticleDOI
Large-Scale Video Classification with Convolutional Neural Networks
TL;DR: This work studies multiple approaches for extending the connectivity of a CNN in time domain to take advantage of local spatio-temporal information and suggests a multiresolution, foveated architecture as a promising way of speeding up the training.
Journal ArticleDOI
Liberals and Conservatives Rely on Different Sets of Moral Foundations
TL;DR: Across 4 studies using multiple methods, liberals consistently showed greater endorsement and use of the Harm/care and Fairness/reciprocity foundations compared to the other 3 foundations, whereas conservatives endorsed and used the 5 foundations more equally.