Social media such as Twitter are a valuable source of information due to their diffusion among citizens and to their speed in sharing data worldwide. However, it is challenging to automatically extract information from such data, given the huge amount of useless content. We propose a multilingual tool that automatically categorizes tweets according to their information content. To achieve real-time classification while supporting any language, we apply a deep learning classifier, using multilingual word embeddings. This allows our solution to be trained on one language and to apply it to any other language via zero-shot inference achieving acceptable performance loss.

Multilingual Text Classification from Twitter during Emergencies / Piscitelli, Sara; Arnaudo, Edoardo; Rossi, Claudio. - ELETTRONICO. - 2021-:(2021), pp. 1-6. (Intervento presentato al convegno 2021 IEEE International Conference on Consumer Electronics, ICCE 2021 tenutosi a Las Vegas (USA) nel 2021) [10.1109/ICCE50685.2021.9427581].

Multilingual Text Classification from Twitter during Emergencies

Arnaudo, Edoardo;
2021

Abstract

Social media such as Twitter are a valuable source of information due to their diffusion among citizens and to their speed in sharing data worldwide. However, it is challenging to automatically extract information from such data, given the huge amount of useless content. We propose a multilingual tool that automatically categorizes tweets according to their information content. To achieve real-time classification while supporting any language, we apply a deep learning classifier, using multilingual word embeddings. This allows our solution to be trained on one language and to apply it to any other language via zero-shot inference achieving acceptable performance loss.
2021
978-1-7281-9766-1
File in questo prodotto:
File Dimensione Formato  
Multilingual_Text_Classification_from_Twitter_during_Emergencies.pdf

accesso riservato

Descrizione: Articolo principale
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.36 MB
Formato Adobe PDF
1.36 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
1570686692.pdf

accesso aperto

Descrizione: Articolo principale, (author's accepted manucript)
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Creative commons
Dimensione 174.27 kB
Formato Adobe PDF
174.27 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2924772