This paper compares Active Learning selection strategies for sentiment analysis of Twitter data. We focus mainly on category-driven strategies, which select training instances taking into consideration the confidence of the system as well as the category of the tweet (e.g. positive or negative). We show that this com- bination is particularly effective when the performance of the system is unbalanced over the different categories. This work was conducted in the framework of automatically ranking the songs of “Festival di Sanremo 2017” based on sentiment analysis of the tweets posted during the contest.

Sanremo's Winner Is... Category-driven Selection Strategies for Active Learning

Anne-Lyse Minard;Manuela Speranza;Mohammed R. H. Qwaider;Bernardo Magnini
2017

Abstract

This paper compares Active Learning selection strategies for sentiment analysis of Twitter data. We focus mainly on category-driven strategies, which select training instances taking into consideration the confidence of the system as well as the category of the tweet (e.g. positive or negative). We show that this com- bination is particularly effective when the performance of the system is unbalanced over the different categories. This work was conducted in the framework of automatically ranking the songs of “Festival di Sanremo 2017” based on sentiment analysis of the tweets posted during the contest.
File in questo prodotto:
File Dimensione Formato  
paper029.pdf

non disponibili

Descrizione: Articolo principale
Licenza: PUBBLICO - Pubblico con Copyright
Dimensione 93.92 kB
Formato Adobe PDF
93.92 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

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: http://hdl.handle.net/11582/315123
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
social impact