Sentiment analysis is one of the most widely studied tasks in natural language processing. While BERT-based models have achieved state-of-the-art results in this task, little attention has been given to its performance variability across class labels, multi-source and multi-domain corpora. In this paper, we present an improved state-of-the-art and comparatively evaluate BERT-based models for sentiment analysis on Italian corpora. The proposed model is evaluated over eight sentiment analysis corpora from different domains (social media, finance, e-commerce, health, travel) and sources (Twitter, YouTube, Facebook, Amazon, Tripadvisor, Opera and Personal Healthcare Agent) on the prediction of positive, negative and neutral classes. Our findings suggest that BERT-based models are confident in predicting positive and negative examples but not as much with neutral examples. We release the sentiment analysis model as well as a newly financial domain sentiment corpus.
Multi-source Multi-domain Sentiment Analysis with BERT-based Models / Roccabruna, G.; Azzolin, Steve; Riccardi, G.. - (2022), pp. 581-589. (Intervento presentato al convegno LREC tenutosi a Marsiglia nel 20th June - 25th June 2022).
Multi-source Multi-domain Sentiment Analysis with BERT-based Models
Roccabruna G.;Azzolin Steve;Riccardi G.
2022-01-01
Abstract
Sentiment analysis is one of the most widely studied tasks in natural language processing. While BERT-based models have achieved state-of-the-art results in this task, little attention has been given to its performance variability across class labels, multi-source and multi-domain corpora. In this paper, we present an improved state-of-the-art and comparatively evaluate BERT-based models for sentiment analysis on Italian corpora. The proposed model is evaluated over eight sentiment analysis corpora from different domains (social media, finance, e-commerce, health, travel) and sources (Twitter, YouTube, Facebook, Amazon, Tripadvisor, Opera and Personal Healthcare Agent) on the prediction of positive, negative and neutral classes. Our findings suggest that BERT-based models are confident in predicting positive and negative examples but not as much with neutral examples. We release the sentiment analysis model as well as a newly financial domain sentiment corpus.File | Dimensione | Formato | |
---|---|---|---|
Multi_source_Multi_domain_Sentiment_Analysis_with_BERT_based_Models.pdf
accesso aperto
Tipologia:
Post-print referato (Refereed author’s manuscript)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
1.68 MB
Formato
Adobe PDF
|
1.68 MB | Adobe PDF | Visualizza/Apri |
2022.lrec-1.62.pdf
accesso aperto
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Creative commons
Dimensione
1.7 MB
Formato
Adobe PDF
|
1.7 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione