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
Book ChapterDOI
Transformer Based Models in Fake News Detection.
TL;DR: In this paper, the authors presented models for detecting fake news and the results of the analyzes of the application of these models, and the precision, f1-score, recall metrics were proposed as a measure of the model quality assessment.
Proceedings ArticleDOI
Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures
TL;DR: In this paper , the authors investigate a new threat to neural sequence-to-sequence (seq2seq) models: training-time attacks that cause models to "spin" their outputs so as to support an adversary-chosen sentiment or point of view.
Journal ArticleDOI
Suspicious news detection through semantic and sentiment measures
Alejandro Martín,Alberto Fernández-Isabel,César González-Fernández,Carmen Lancho,Marina Cuesta,Isaac Martín de Diego +5 more
TL;DR: In this article, the authors presented the Knowledge Recovering Architecture based on Keywords Extraction from Narratives for Suspicious News Detection (KRAKEN-SND) system, which supports human experts to detect suspicious news articles that should be verified.
Proceedings Article
Computing with Subjectivity Lexicons
Caio Libânio Melo Jerônimo,Cláudio E. C. Campelo,Leandro Balby Marinho,Allan Sales,Adriano Veloso,Roberta Viola +5 more
TL;DR: A new set of lexicons for expressing subjectivity in text documents written in Brazilian Portuguese, in contrast to other subjectivity lexicons available, these lexicons represent different subjectivity dimensions and are more compact in number of terms.
Posted Content
Anchored in a Data Storm: How Anchoring Bias Can Affect User Strategy, Confidence, and Decisions in Visual Analytics.
TL;DR: The findings reveal that strategy cues and visual anchors can significantly affect user activity, speed, confidence, and, under certain circumstances, accuracy.
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.