In recent years, sentiment analysis received a great deal of attention due to the accelerated evolution of the Internet, by which people all around the world share their opinions and comments on different topics such as sport, politics, movies, music and so on. The result is a huge amount of available unstructured information. In order to detect positive or negative subject’s sentiment from this kind of data, sentiment analysis technique is widely used. In this context, here, we introduce an ensemble classifier for Persian sentiment analysis using shallow and deep learning algorithms to improve the performance of the state-of-art approaches. Specifically, experimental results show that the proposed ensemble classifier achieved accuracy rate up to 79.68%.

An Ensemble Based Classification Approach for Persian Sentiment Analysis

Ieracitano C.
;
Morabito F. C.;
2021-01-01

Abstract

In recent years, sentiment analysis received a great deal of attention due to the accelerated evolution of the Internet, by which people all around the world share their opinions and comments on different topics such as sport, politics, movies, music and so on. The result is a huge amount of available unstructured information. In order to detect positive or negative subject’s sentiment from this kind of data, sentiment analysis technique is widely used. In this context, here, we introduce an ensemble classifier for Persian sentiment analysis using shallow and deep learning algorithms to improve the performance of the state-of-art approaches. Specifically, experimental results show that the proposed ensemble classifier achieved accuracy rate up to 79.68%.
2021
978-981-15-5092-8
978-981-15-5093-5
Deep learning
Ensemble classifier
Natural language processing
Persian sentiment analysis
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/20.500.12318/66654
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 16
  • ???jsp.display-item.citation.isi??? ND
social impact