Sentiment Analysis for Fake News Detection

Abstract

In recent years, we have witnessed a rise in fake news, i.e., provably false pieces of information created with the intention of deception. The dissemination of this type of news poses a serious threat to cohesion and social well-being, since it fosters political polarization and the distrust of people with respect to their leaders. The huge amount of news that is disseminated through social media makes manual verification unfeasible, which has promoted the design and implementation of automatic systems for fake news detection. The creators of fake news use various stylistic tricks to promote the success of their creations, with one of them being to excite the sentiments of the recipients. This has led to sentiment analysis, the part of text analytics in charge of determining the polarity and strength of sentiments expressed in a text, to be used in fake news detection approaches, either as a basis of the system or as a complementary element. In this article, we study the different uses of sentiment analysis in the detection of fake news, with a discussion of the most relevant elements and shortcomings, and the requirements that should be met in the near future, such as multilingualism, explainability, mitigation of biases, or treatment of multimedia elements.

Deceptive Online Content Detection Using Only Message Characteristics and a Machine Learning Trained Expert System

“…The lack of comparison searching also facilitates fast analysis. Known truthful and deceptive text are analyzed to identify linguistic patterns (such as word usage, n-gram and syntactic structure, semantic similarities, and rhetorical relationships between linguistic elements) associated with deceptive content [10]. Hancock's method of analyzing individual words and n-grams (referred to as the "bags of words" technique) is very straightforward.…”

“…This approach focuses on the emotions of the text. The theoretical basis of this approach is that fake news authors often intentionally arouse the emotions of the readers to drive the success of their articles [10].…”

“…Sentiment analysis determines the type and intensity of the emotions expressed in text [10]. It is a branch of natural language processing which seeks to determine whether a text conveys objective or subjective information.…”

“…If subjective information is identified, it is further assessed to determine whether it is presented in a positive, neutral, or negative manner, and whether it is expressed strongly or weekly. This technique is also referred to as opinion mining [10].…”

“…However, these systems require a method to identify the deceptive content, in order to take whatever mitigation action that they propose. Strategies such as textual analysis [10,11], article characteristics analysis [12], and network analysis [13] have been proposed.…”