With restrictions aimed at limiting travel and with the introduction, during the most critical moments of the COVID-19 pandemic, of bans that prevented people from leaving their homes, the platforms known as "social media" became an outlet for users to express their concerns, opinions and moods caused by the pandemic itself. People, as well as health agencies and governments, are still using Twitter as one of the main means of communication and information. Since the beginning of the pandemic, millions of tweets related to the topic have been posted. For this reason, since Twitter is also a protagonist of the reality we are living, it can, and has been, used not only to share news and information, but also to collect data aimed at providing an analysis of the current situation, both from a temporal and geospatial point of view. Thus, the objectives of this study are to examine how the social phenomenon has evolved in relation to the pandemic phenomenon, thereby exploring how the key topics covered and the sentiment associated with them have changed in time. Based on a collection of 4.6 million COVID-19-related tweets from February 2020 to December 2020, we sought a correlation between the amount of tweets posted in a day and coronavirus infections per day. In addition we analyse the sentiments and the topic covered of the users of the Twitter social media platform by perform Topic Modeling and Sentiment Classification. Finally, in order to have a more extensive overview of the still evolving situation, we analyzed the countries most involved at the infectious and media level.
Con le restrizioni volte a limitare gli spostamenti e con l’introduzione, nei momenti di maggior criticità della pandemia di COVID-19, di veri e propri divieti che impedivano di uscire dalla propria abitazione, le piattaforme note come “social media” sono diventate uno sbocco per gli utenti, i quali hanno così potuto esprimere le loro preoccupazioni, le loro opinioni e gli stati d’animo altalenati causati dalla pandemia stessa. Le persone, così come le agenzie sanitarie e i Governi, stanno tuttora usando Twitter come uno dei principali mezzi di comunicazione e informazione. Dall'inizio della pandemia sono stati postati milioni di tweet relativi all'argomento. Per questo motivo, essendo Twitter anche lui protagonista della realtà che stiamo vivendo, può, ed è stato, utilizzando, oltre che per la condivisione di novità e informazioni, anche per la raccolta dati volti a fornire un’analisi della situazione in corso, sia dal punto di vista temporale, sia geospaziale. Gli obiettivi di questo studio sono quindi volti ad esaminare come si è evoluto il fenomeno social in relazione a quello pandemico, esplorando in questo modo come siano cambiati, nel corso del 2020, gli argomenti chiave trattati e i sentimenti ad essi associati. Sulla base di una raccolta di 4,6 milioni di tweet relativi al COVID-19 da febbraio 2020 a dicembre 2020, abbiamo cercato una correlazione tra la quantità di tweet pubblicati in un giorno e le infezioni da coronavirus al giorno. Inoltre abbiamo analizzato i sentimenti e gli argomenti trattati dagli utenti della piattaforma Twitter eseguendo Topic Modeling e Sentiment Classification. Infine, per avere una panoramica più estesa della situazione ancora in evoluzione, si sono analizzati i paesi maggiormente coinvolti a livello infettivo e livello mediatico.
Analyzing social media activity related to the COVID-19 pandemic
Carughi, Alessandro
2019/2020
Abstract
With restrictions aimed at limiting travel and with the introduction, during the most critical moments of the COVID-19 pandemic, of bans that prevented people from leaving their homes, the platforms known as "social media" became an outlet for users to express their concerns, opinions and moods caused by the pandemic itself. People, as well as health agencies and governments, are still using Twitter as one of the main means of communication and information. Since the beginning of the pandemic, millions of tweets related to the topic have been posted. For this reason, since Twitter is also a protagonist of the reality we are living, it can, and has been, used not only to share news and information, but also to collect data aimed at providing an analysis of the current situation, both from a temporal and geospatial point of view. Thus, the objectives of this study are to examine how the social phenomenon has evolved in relation to the pandemic phenomenon, thereby exploring how the key topics covered and the sentiment associated with them have changed in time. Based on a collection of 4.6 million COVID-19-related tweets from February 2020 to December 2020, we sought a correlation between the amount of tweets posted in a day and coronavirus infections per day. In addition we analyse the sentiments and the topic covered of the users of the Twitter social media platform by perform Topic Modeling and Sentiment Classification. Finally, in order to have a more extensive overview of the still evolving situation, we analyzed the countries most involved at the infectious and media level.File | Dimensione | Formato | |
---|---|---|---|
Analyzing Social Media Activity Related to the COVID-19 Pandemic.pdf
accessibile in internet per tutti
Dimensione
4.07 MB
Formato
Adobe PDF
|
4.07 MB | Adobe PDF | Visualizza/Apri |
I documenti in POLITesi sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/10589/174928