Combining Vagueness Detection with Deep Learning to Identify Fake News

TL;DR

This paper integrates semantic rule-based vagueness detection with deep learning classification to improve fake news identification, demonstrating mutual benefits and correlation between vagueness measures and bias classification.

Contribution

It introduces a combined approach using VAGO and FAKE-CLF, merging rule-based and deep learning methods for more effective fake news detection.

Findings

Positive correlation between vagueness and bias classification

VAGO explains FAKE-CLF results effectively

FAKE-CLF expands VAGO's database

Abstract

In this paper, we combine two independent detection methods for identifying fake news: the algorithm VAGO uses semantic rules combined with NLP techniques to measure vagueness and subjectivity in texts, while the classifier FAKE-CLF relies on Convolutional Neural Network classification and supervised deep learning to classify texts as biased or legitimate. We compare the results of the two methods on four corpora. We find a positive correlation between the vagueness and subjectivity measures obtained by VAGO, and the classification of text as biased by FAKE-CLF. The comparison yields mutual benefits: VAGO helps explain the results of FAKE-CLF. Conversely FAKE-CLF helps us corroborate and expand VAGO's database. The use of two complementary techniques (rule-based vs data-driven) proves a fruitful approach for the challenging problem of identifying fake news.