Harvey Mudd College at SemEval-2019 Task 4: The D.X. Beaumont Hyperpartisan News Detector

Amason, Evan; Palanker, Jake; Shen, Mary Clare; Medero, Julie

doi:10.18653/v1/s19-2166

Cited by 2 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This involves studying textual information within articles using style-based or topicbased models (Sánchez-Junquera et al, 2021;Potthast et al, 2018;Lyu et al, 2023;Smȃdu et al, 2023). Detection methods may begin with specific sections, such as the title (Lyu et al, 2023;Amason et al, 2019), sentences (jeong Lim et al, 2018), quotes in the body (Pérez-Almendros et al, 2019), or encompass both (Naredla and Adedoyin, 2022;Gangula et al, 2019;Papadopoulou et al, 2019;Lyu et al, 2023;Nguyen et al, 2019). On the other hand, the entities involved in the writing and publishing process were taken into account.…”

Section: Where Can Hyperpartisanship Be Detected? Perspectives On The...mentioning

confidence: 99%

“…From a linguistic point of view, hyperpartisan articles exhibit a high adjective and adverbs count (Pérez-Almendros et al, 2019;Dumitru and Rebedea, 2019), massive use of pronouns and words of disgust (Knauth, 2019), tending to write longer paragraphs (Hanawa et al, 2019) with a sensationalist style full of emotional language and rare terms (Sengupta and Pedersen, 2019). It has been proven that right-media often tend to write hyperpartisan headlines (Lyu et al, 2023), and that news especially shows hyperpartisan traits in the titles (Amason et al, 2019).…”

Section: Definitions and Characteristicsmentioning

confidence: 99%

See 1 more Smart Citation

A systematic review of Hyperpartisan News detection: A Comprehensive Framework for Definition, Detection, and Evaluation

Maggini,

Bassi,

Otero

et al. 2024

Preprint

View full text Add to dashboard Cite

Hyperpartisan news detection employs advanced technological methods to identify news articles characterized by extreme bias, reporting information in a highly polarized manner. The spread of such news could lead to detrimental effects in terms of social cohesion and facts-perception. This systematic review delves into the uncharted territory of hyperpartisan news detection, where a conspicuous absence of comprehensive studies has left a void in scholarly discourse. Following the PRISMA methodology, we selected 80 pertinent articles. The paper commences by addressing the inherent challenges arising from disparate and ambiguous definitions of hyperpartisan found in existing literature. Through a meticulous analysis, we propose a refined and comprehensive definition of hyperpartisan news, serving as a foundational framework for subsequent exploration. The review systematically evaluates Non-Deep Learning, Deep Learning (i.e. non-Transformer and Transformer-based methods), and mixed approaches employed in the identification of hyperpartisan content across various studies. By scrutinizing methodologies, algorithms, and key features, we categorize and compare their performances, shedding light on their efficacy and limitations. Furthermore, we conducted an examination of 36 datasets utilized in diverse studies, offering insights into the commonalities and variations in data sources. This inclusive dataset analysis contributes to a nuanced understanding of the challenges faced in the development and validation of hyperpartisan news detection models. This paper not only pioneers the systematic review of hyperpartisan news detection, but also establishes a robust foundation for future research endeavors in this critical domain. We emphasize the necessity of standardized definitions, rigorous evaluation metrics, and shared datasets to advance the field.

show abstract

Section: Where Can Hyperpartisanship Be Detected? Perspectives On The...mentioning

confidence: 99%

Section: Definitions and Characteristicsmentioning

confidence: 99%

A systematic review of Hyperpartisan News detection: A Comprehensive Framework for Definition, Detection, and Evaluation

Maggini,

Bassi,

Otero

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

SemEval-2019 Task 4: Hyperpartisan News Detection

Kiesel¹,

Mestre²,

Shukla³

et al. 2019

Proceedings of the 13th International Workshop on Semantic Evaluation

163

170

View full text Add to dashboard Cite

Hyperpartisan news is news that takes an extreme left-wing or right-wing standpoint. If one is able to reliably compute this meta information, news articles may be automatically tagged, this way encouraging or discouraging readers to consume the text. It is an open question how successfully hyperpartisan news detection can be automated, and the goal of this SemEval task was to shed light on the state of the art. We developed new resources for this purpose, including a manually labeled dataset with 1,273 articles, and a second dataset with 754,000 articles, labeled via distant supervision. The interest of the research community in our task exceeded all our expectations: The datasets were downloaded about 1,000 times, 322 teams registered, of which 184 configured a virtual machine on our shared task cloud service TIRA, of which in turn 42 teams submitted a valid run. The best team achieved an accuracy of 0.822 on a balanced sample (yes : no hyperpartisan) drawn from the manually tagged corpus; an ensemble of the submitted systems increased the accuracy by 0.048.

show abstract

Harvey Mudd College at SemEval-2019 Task 4: The D.X. Beaumont Hyperpartisan News Detector

Cited by 2 publications

References 4 publications

A systematic review of Hyperpartisan News detection: A Comprehensive Framework for Definition, Detection, and Evaluation

A systematic review of Hyperpartisan News detection: A Comprehensive Framework for Definition, Detection, and Evaluation

SemEval-2019 Task 4: Hyperpartisan News Detection

Contact Info

Product

Resources

About