Pregled bibliografske jedinice broj: 1179288
NLP based framework for the comparison of the media coverage in Croatia during the first two waves of the COVID-19 pandemic
NLP based framework for the comparison of the media coverage in Croatia during the first two waves of the COVID-19 pandemic // Odjeci SCIMETH-a (izazovi lingvističkih istraživanja) / Nigoević, Magdalena ; Vlastelić, Anastazija (ur.).
Split: Filozofski fakultet Sveučilišta u Splitu ; Centar za jezična istraživanja Filozofskog fakulteta Sveučilišta u Rijeci ; Hrvatsko društvo za primijenjenu lingvistiku (HDPL), 2021. str. 169-190
CROSBI ID: 1179288 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
NLP based framework for the comparison of the media coverage in Croatia during the first two waves of the COVID-19 pandemic
Autori
Beliga, Slobodan ; Meštrović, Ana ; Matešić, Mihaela
Vrsta, podvrsta i kategorija rada
Poglavlja u knjigama, znanstveni
Knjiga
Odjeci SCIMETH-a (izazovi lingvističkih istraživanja)
Urednik/ci
Nigoević, Magdalena ; Vlastelić, Anastazija
Izdavač
Filozofski fakultet Sveučilišta u Splitu ; Centar za jezična istraživanja Filozofskog fakulteta Sveučilišta u Rijeci ; Hrvatsko društvo za primijenjenu lingvistiku (HDPL)
Grad
Split
Godina
2021
Raspon stranica
169-190
ISBN
978-953-352-071-1
Ključne riječi
online news media ; infoveillance ; crisis communication ; natural language processing
Sažetak
Online media play an important role in public health emergencies and serve as a communication platform. Infoveillance of online media during the COVID-19 pandemic is an important step towards a better understanding of crisis communication. The goal of this study was to perform a longitudinal analysis of the COVID-19-related content based on natural language processing methods. We present a possible framework for monitoring media coverage of crisis communication. For this purpose, we collected a dataset of news articles published by Croatian online media during the first 13 months of the pandemic. As the first step, we calculated the percentage of COVID-19-related articles in the total number of articles across eight online news media for different periods of the pandemic. The second step was to analyze the content by extracting the most frequent terms and applying the Jaccard similarity. Next, we compared the occurrence of the pandemic-related terms during the two waves of the pandemic. Finally, we applied named entity recognition to extract the most frequent entities and track the dynamics of changes during the observed period. The results reveal that the online media have promptly responded to the pandemic with a large number of COVID-19-related articles. The total number of COVID- 19-related articles in online media is rather high – even in the period between the two waves of the epidemic, when the number of new cases dropped to zero, the number of publications related to the COVID-19 topics remained high. Furthermore, there are large overlaps in the terminology used in all articles published during the pandemic with a slight shift in the pandemic- related terms between the first and the second wave. Finally, our findings indicate that the most influential entities have lower overlaps for identified persons and higher overlaps for locations.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti, Filologija
POVEZANOST RADA
Projekti:
HRZZ-IP-CORONA-2020-04-2061 - Višeslojni okvir za karakterizaciju širenja informacija putem društvenih medija tijekom krize COVID-19 (InfoCoV) (Meštrović, Ana, HRZZ - 2020-04) ( CroRIS)
Ustanove:
Filozofski fakultet, Rijeka,
Fakultet informatike i digitalnih tehnologija, Rijeka