Fact vs. Opinion: the Role of Argumentation Features in News Classification

Alhindi, Tariq; Muresan, Smaranda; Preoţiuc-Pietro, Daniel

doi:10.18653/v1/2020.coling-main.540

Cited by 10 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This conceptualization enables us to add evidence estimating the audience's perception to the established newsroom-centered research. In addition, complementing the previous computational linguistic studies on news classification and formality detection (Alhindi, Muresan, and Preot ¸iuc-Pietro 2020;Pavlick and Tetreault 2016), this study sheds light on the "demand-side" with rather subjective annotations provided by actual news consumers (Costera Meijer 2020).…”

Section: Discussionmentioning

confidence: 70%

“…Following Alhindi, Muresan, and Preot ¸iuc-Pietro (2020), we chose the BERT model for sentence classification in both tasks (Devlin et al 2018). To be more context-specific, a monolingual Dutch model (i.e., BERTje) that based on a diverse dataset containing three news corpora was chosen over the original one that only based on Wikipedia text (De Vries et al 2019).…”

Section: Model Trainingmentioning

confidence: 99%

See 1 more Smart Citation

Beyond Discrete Genres: Mapping News Items onto a Multidimensional Framework of Genre Cues

Lin¹,

Welbers²,

Vermeer³

et al. 2023

ICWSM

View full text Add to dashboard Cite

In the contemporary media landscape, with the vast and diverse supply of news, it is increasingly challenging to study such an enormous amount of items without a standardized framework. Although attempts have been made to organize and compare news items on the basis of news values, news genres receive little attention, especially the genres in a news consumer’s perception. Yet, perceived news genres serve as an essential component in exploring how news has developed, as well as a precondition for understanding media effects. We approach this concept by conceptualizing and operationalizing a non-discrete framework for mapping news items in terms of genre cues. As a starting point, we propose a preliminary set of dimensions consisting of “factuality” and “formality”. To automatically analyze a large amount of news items, we deliver two computational models for predicting news sentences in terms of the said two dimensions. Such predictions could then be used for locating news items within our framework. This proposed approach that positions news items upon a multidimensional grid helps deepening our insight into the evolving nature of news genres.

show abstract

Section: Discussionmentioning

confidence: 70%

Section: Model Trainingmentioning

confidence: 99%

Beyond Discrete Genres: Mapping News Items onto a Multidimensional Framework of Genre Cues

Lin¹,

Welbers²,

Vermeer³

et al. 2023

ICWSM

View full text Add to dashboard Cite

show abstract

“…These earlier approaches rely on engineered lexical features which are not robust against changes in topics and not generalisable to unseen (during training) news publishers. Recently, Alhindi et al ( 2020 ) combine argumentation features and computational language models like BERT 6 (Devlin et al, 2019 ) to identify news vs. opinion. They show promising performance in comparison to previous approaches across datasets and publishers.…”

Section: Discussionmentioning

confidence: 99%

Understanding image-text relations and news values for multimodal news analysis

Cheema

Hakimov

Müller-Budack

et al. 2023

Front. Artif. Intell.

View full text Add to dashboard Cite

The analysis of news dissemination is of utmost importance since the credibility of information and the identification of disinformation and misinformation affect society as a whole. Given the large amounts of news data published daily on the Web, the empirical analysis of news with regard to research questions and the detection of problematic news content on the Web require computational methods that work at scale. Today's online news are typically disseminated in a multimodal form, including various presentation modalities such as text, image, audio, and video. Recent developments in multimodal machine learning now make it possible to capture basic “descriptive” relations between modalities–such as correspondences between words and phrases, on the one hand, and corresponding visual depictions of the verbally expressed information on the other. Although such advances have enabled tremendous progress in tasks like image captioning, text-to-image generation and visual question answering, in domains such as news dissemination, there is a need to go further. In this paper, we introduce a novel framework for the computational analysis of multimodal news. We motivate a set of more complex image-text relations as well as multimodal news values based on real examples of news reports and consider their realization by computational approaches. To this end, we provide (a) an overview of existing literature from semiotics where detailed proposals have been made for taxonomies covering diverse image-text relations generalisable to any domain; (b) an overview of computational work that derives models of image-text relations from data; and (c) an overview of a particular class of news-centric attributes developed in journalism studies called news values. The result is a novel framework for multimodal news analysis that closes existing gaps in previous work while maintaining and combining the strengths of those accounts. We assess and discuss the elements of the framework with real-world examples and use cases, setting out research directions at the intersection of multimodal learning, multimodal analytics and computational social sciences that can benefit from our approach.

show abstract

“…From an empirical perspective, a few studies have leveraged argumentative features with the overall goal of advancing fake news detection. Alhindi et al (2020) have shown that argumentative components constitute relevant features to build classifiers able to automatically distinguish opinion articles from news stories and, thus, help fact checkers distinguishing facts from opinions. Focusing on semantic content rather than genre, Kotonya and Toni (2019) have built a system for stance detection that aggregates multiple stance labels from different text sources upon a claim to predict its veracity, assuming that (dis)agreement expressed by sources with high credibility is tied to claim trustworthiness.…”

Section: Argumentation and Fake Newsmentioning

confidence: 99%

Staying Up to Date with Fact and Reason Checking: An Argumentative Analysis of Outdated News

Musi

Rocci

2022

The Pandemic of Argumentation

View full text Add to dashboard Cite

This paper tackles outdated news about COVID-19 as a type of misinformation from an argumentative perspective, focusing on the fact-checker Snopes. In rapidly changing information environments the circulation of outdated news can be highly detrimental causing risky behaviors. Such type of misinformation is difficult to pin down through fact-checking since encompassing different types of contents, motivations and channels. To fully understand this phenomenon we deem necessary to move away from a naïve view of fact checking to an argumentative one. But what are the argumentative configurations of outdated statements in the context of the current information ecosystem? To answer this question we rely on the distinction between upstream and downstream argumentation to anchor the kind of issues put forward by outdated statements. We then take as a sample all the news that have been rated as “outdated” and “miscaptioned” by Snopes during the pandemic and analyse the type of source, the semantic type of news claim and the argumentative role played by the outdated information. We come up with an argumentative taxonomy of outdated news where the presence of multimodal information as well as the semantic-argumentative role played by outdated statements pattern with the spread of mis- and disinformation.

show abstract

Fact vs. Opinion: the Role of Argumentation Features in News Classification

Cited by 10 publications

References 16 publications

Beyond Discrete Genres: Mapping News Items onto a Multidimensional Framework of Genre Cues

Beyond Discrete Genres: Mapping News Items onto a Multidimensional Framework of Genre Cues

Understanding image-text relations and news values for multimodal news analysis

Staying Up to Date with Fact and Reason Checking: An Argumentative Analysis of Outdated News

Contact Info

Product

Resources

About