Incongruent Headlines: Yet Another Way to Mislead Your Readers

Abstract

This paper discusses the problem of incongruent headlines: those which do not accurately represent the information contained in the article with which they occur. We emphasise that this phenomenon should be considered separately from recognised problematic headline types such as clickbait and sensationalism, arguing that existing natural language processing (NLP) methods applied to these related concepts are not appropriate for the automatic detection of headline incongruence, as an analysis beyond stylistic traits is necessary. We therefore suggest a number of alternative methodologies that may be appropriate to the task at hand as a foundation for future work in this area. In addition, we provide an analysis of existing data sets which are related to this work, and motivate the need for a novel data set in this domain.

From Stances' Imbalance to Their HierarchicalRepresentation and Detection

“…The task of stance detection is to identify the stance of an evidence towards a given news claim [12,13]. Stances can be categorized into four classes: agree, disagree, discuss and unrelated [17].…”

The Influence of Traits Associated with Autism Spectrum Disorder (ASD) on the Detection of Fake News

“…In order to categorise these articles, the definition of 'emotive' as given by the Oxford Dictionary of English (Stevenson, 2010) was used, where an emotive issue is one 'expressing a person's feelings rather than being neutrally descriptive'. As suggested by Chesney, Liakata, Poesio & Purver (2017), use of emotive language often relates to particular topics in fake news and evokes emotion or empathy from the reader. The pilot sample then also categorised the article headlines and two discrepancies were discussed and a final set of headlines was produced.…”

“…Horne and Adah, (2017), suggest that when attempting to differentiate between fake and real news, the title or headline of an article can be a strong indicator, due purely to its wording and structure. Headlines using emotive language are often associated with topics such as scandal, crime or disaster (Chesney, Liakata, Poesio & Purver, 2017). Exaggeration, embellishment and use of emotive language is often a prominent feature in sensationalist news, especially fake news and clickbait headlines (Molek-Kozakowska, 2013).…”

Learning to Detect Incongruence in News Headline and Body Text via a Graph Neural Network

“…This study aims to tackle the headline incongruity problem [5], which involves determining whether the news headlines are unrelated to or distinct from the main parts of the full body text. Figure 1 illustrates an example in which based solely on the headline, a reader might expect to learn specific information related to the novel coronavirus; however, the body text contains an advertisement for a dietary supplement.…”