DiversiNews: Surfacing Diversity in Online News

Trampus, Mitja; Fuart, Flavio; Pighin, Daniele; Štajner, Tadej; Berčič, Jan; Novak, Blaž; Rusu, Delia; Stopar, Luka; Grobelnik, Marko

doi:10.1609/aimag.v36i4.2528

Cited by 7 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, if recommender systems are better able to understand the bias of news articles through their framing, they will be able to better suit their users' taste [16]. On the other hand, the results can be used by news aggregators who wish to provide a less-biased view of news stories to their audience [26,37,53], and to overcome "filter bubbles" [43].…”

Section: Discussionmentioning

confidence: 99%

Untitled

2018

Trans. Soc. Comput.

View full text Add to dashboard Cite

It has been observed that different media outlets exert bias in the way they report the news, which seamlessly influences the way that readers' knowledge is built through filtering what we read. Therefore, understanding bias in news media is fundamental for obtaining a holistic view of a news story. Traditional work has focused on biases in terms of "agenda setting," where more attention is allocated to stories that fit their biased narrative. The corresponding method is straightforward, since the bias can be detected through counting the occurrences of different stories/themes within the documents. However, these methods are not applicable to biases which are implicit in wording, namely, "framing" bias. According to framing theory, biased communicators will select and emphasize certain facts and interpretations over others when telling their story. By focusing on facts and interpretations that conform to their bias, they can tell the story in a way that suits their narrative. Automatic detection of framing bias is challenging since nuances in the wording can change the interpretation of the story. In this work, we aim to investigate how the subtle pattern hidden in language use of a news agency can be discovered and further leveraged to detect frames. In particular, we aim to identify the type and polarity of frame in a sentence. Extensive experiments are conducted on real-world data from different countries. A case study is further provided to reveal possible applications of the proposed method. CCS Concepts: • Human-centered computing → Collaborative and social computing; • Information systems → Web mining;

show abstract

Section: Discussionmentioning

confidence: 99%

Untitled

2018

Trans. Soc. Comput.

View full text Add to dashboard Cite

show abstract

“…We consider front pages as a reliable reflection of the information many users are exposed to whilst visiting these websites. This is opposed to other article collection strategies, such as RSS or downloading the entire website content, that have limited control over assessing how many people have actually read any given article 16,30 . Focusing our analysis efforts on articles from landing pages in major ONSs, gives us an opportunity to assess the number of COVID-19-related articles a large proportion of online news consumers might have been exposed to.…”

Section: Methodsmentioning

confidence: 99%

Quantifying the online news media coverage of the COVID-19 pandemic

Krawczyk

Chełkowski

Mishra

et al. 2020

Preprint

View full text Add to dashboard Cite

BackgroundNon-pharmaceutical interventions such as lockdowns, mask wearing and social distancing have been the primary measures to effectively combat the COVID-19 pandemic. Such measures are highly effective when there is strong population wide adherence which needs to be facilitated by information on the current risks posed by the pandemic alongside a clear exposition of the rules and guidelines in place. Here we address the issue of communication on the pandemic by offering data and analysis of online news media coverage of COVID-19.MethodsWe collected 26 million news articles from the front pages of 172 major online news sources in 11 countries (available at http://sciride.org). Using topic detection we identified COVID-19-related content to quantify the proportion of total coverage pandemic received in 2020. Sentiment analysis tool Vader was employed to stratify the emotional polarity of COVID-19 reporting. Further topic detection and sentiment analysis was performed on COVID-19 articles to reveal the leading themes in pandemic reporting and their respective emotional polarizations.FindingsWe find that COVID-19 coverage accounted for approximately 25% of all front-page online news articles between January and October 2020. Sentiment analysis of English-speaking sources reveals that the overall COVID-19 coverage cannot be simply classified as negative due to the disease subject matter, suggesting a wide heterogeneous reporting of the pandemic. Within this heterogenous coverage, 16% of COVID-19 news articles (or 4% of all English-speaking articles) can be classified as highly negatively polarized, citing issues such as death, fear or crisis.InterpretationThe goal of pandemic public health communication is to increase understanding of distancing rules and maximize the impact of any governmental policy. Our results suggest an information overload in COVID-19 reporting that could risk obscuring effective policy communication. We hope that our data and analysis will inform health communication strategy to minimize the risks of COVID-19 while vaccination regimes are being introduced.

show abstract

“…In this work we implemented cross-linking of clusters for three language pairs. 45 The approach described in this paper is a crucial component of an extension of the iDiversiNews application [9], which will allow users to explore related news stories in different languages and discover new aspects of a story. A similar approach 50 is used in the Event Registry application [10] for detection of events from multilingual news article data.…”

Section: Introductionmentioning

confidence: 99%