A Text Similarity Study: Understanding How Differently Greek News Media Describe News Events
Authors: Kapellas, Nikos 
Kapidakis, Sarantos 
Issue Date: 1-Jan-2022
Conference: International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2022) 
Book: Proceedings of the 14th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2022) 
Volume: 2
Keywords: Cosine Similarity, Greek News Media, News Articles, News Events, Similarity Analysis
Abstract: 
Online news media usually cover the same news events. It would be interesting to understand, how similar are the descriptions of these events. In other words to explore how a distinct news event, is described by different news media. Can we safely conclude when two or more event descriptions refer to the same event? This research aims to investigate similarities in Greek news articles and provide new data on the field, as there is no relevant research. To do so, news article’s text is extracted, processed and analyzed with automated methods. To establish an understanding of similarity, three similarity settings are explored and special focus is given in examining the degree of similarity between news articles that cover the same event. In some cases results are inconclusive, while in others results show that groups of news media share the exact same articles with little or no modifications at all. The similarity analysis of news articles is a complex task and relies on many different factors that need to be addressed.
ISBN: 9789897586149
ISSN: 21843228
DOI: 10.5220/0011589700003335
URI: https://uniwacris.uniwa.gr/handle/3000/788
Type: Conference Paper
Department: Department of Archival, Library and Information Studies 
School: School of Administrative, Economics and Social Sciences 
Affiliation: University of West Attica (UNIWA) 
Appears in Collections:Book Chapter / Κεφάλαιο Βιβλίου

CORE Recommender
Show full item record

SCOPUSTM   
Citations 50

1
checked on Oct 30, 2024

Page view(s)

52
checked on Nov 5, 2024

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.