This experimental paper proposes a sentiment analysis of data from Twitter, with the aim of monitoring the corporate reputation of five airlines during the crisis period of summer 2022. The sentiment of users who express themselves on four airline services is detected through the analysis of a corpus containing the tweets users published. In addition, a corpus of tweets published by official airline accounts is created to verify if they treated certain topics with the same attention as users. After providing a theoretical and methodological basis for the definition and measurement of reputation, the procedure used to analyze the data is explained, which involved the use of the Twitter API, the Python programming language, and the VADER (Valence Aware Dictionary and sEntiment Reasoner) module.
Il presente elaborato sperimentale propone una sentiment analysis dei dati provenienti da Twitter, con l’obiettivo di monitorare la reputazione aziendale di cinque compagnie aeree nel periodo di crisi dell’estate 2022. Il sentiment degli utenti che si esprimono su quattro servizi delle compagnie aeree viene rilevato attraverso l'analisi di un corpus contenente i tweet da essi pubblicati. Inoltre, viene costituito anche un corpus relativo ai tweet pubblicati dagli account ufficiali delle compagnie aeree per verificare se esse trattano determinati argomenti con la stessa attenzione degli utenti. Dopo aver fornito una base teorica e metodologica per la definizione e la misurazione della reputazione, si illustra la procedura utilizzata per analizzare i dati, che ha previsto l’utilizzo delle Twitter API, del linguaggio di programmazione Python e del modulo VADER (Valence Aware Dictionary and sEntiment Reasoner).
Sentiment analysis per il monitoraggio della reputazione su Twitter delle compagnie aeree: il periodo di crisi dell’estate 2022
PASQUALINI, GIULIA
2022/2023
Abstract
This experimental paper proposes a sentiment analysis of data from Twitter, with the aim of monitoring the corporate reputation of five airlines during the crisis period of summer 2022. The sentiment of users who express themselves on four airline services is detected through the analysis of a corpus containing the tweets users published. In addition, a corpus of tweets published by official airline accounts is created to verify if they treated certain topics with the same attention as users. After providing a theoretical and methodological basis for the definition and measurement of reputation, the procedure used to analyze the data is explained, which involved the use of the Twitter API, the Python programming language, and the VADER (Valence Aware Dictionary and sEntiment Reasoner) module.File | Dimensione | Formato | |
---|---|---|---|
Pasqualini_Giulia.pdf
accesso aperto
Dimensione
6.94 MB
Formato
Adobe PDF
|
6.94 MB | Adobe PDF | Visualizza/Apri |
The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License
https://hdl.handle.net/20.500.12608/46604