The fabulous results of convolution neural networks in image-related tasks attracted attention of text mining, sentiment analysis and other text analysis researchers. It is, however, difficult to find enough data for feeding such networks, optimize their parameters, and make the right design choices when constructing network architectures. The purpose of this paper is to present the creation steps of two big data sets of song emotions. The authors also explore usage of convolution and max-pooling neural layers on song lyrics, product and movie review text data sets. Three variants of a simple and flexible neural network architecture are also compared. The intention was to spot any important patterns that can serve as guidelines for parameter optimization of similar models. The authors also wanted to identify architecture design choices which lead to high performing sentiment analysis models. To this end, the authors conducted a series of experiments with neural architectures of various configurations. The results indicate that parallel convolutions of filter lengths up to 3 are usually enough for capturing relevant text features. Also, max-pooling region size should be adapted to the length of text documents for producing the best feature maps. Top results the authors got are obtained with feature maps of lengths 6–18. An improvement on future neural network models for sentiment analysis could be generating sentiment polarity prediction of documents using aggregation of predictions on smaller excerpt of the entire text.

A Data-driven Neural Network Architecture for Sentiment Analysis / Çano, Erion; Morisio, Maurizio. - In: DATA TECHNOLOGIES AND APPLICATIONS. - ISSN 2514-9288. - ELETTRONICO. - 53:1(2019), pp. 2-19. [10.1108/DTA-03-2018-0017]

A Data-driven Neural Network Architecture for Sentiment Analysis

Çano, Erion;Morisio, Maurizio
2019

Abstract

The fabulous results of convolution neural networks in image-related tasks attracted attention of text mining, sentiment analysis and other text analysis researchers. It is, however, difficult to find enough data for feeding such networks, optimize their parameters, and make the right design choices when constructing network architectures. The purpose of this paper is to present the creation steps of two big data sets of song emotions. The authors also explore usage of convolution and max-pooling neural layers on song lyrics, product and movie review text data sets. Three variants of a simple and flexible neural network architecture are also compared. The intention was to spot any important patterns that can serve as guidelines for parameter optimization of similar models. The authors also wanted to identify architecture design choices which lead to high performing sentiment analysis models. To this end, the authors conducted a series of experiments with neural architectures of various configurations. The results indicate that parallel convolutions of filter lengths up to 3 are usually enough for capturing relevant text features. Also, max-pooling region size should be adapted to the length of text documents for producing the best feature maps. Top results the authors got are obtained with feature maps of lengths 6–18. An improvement on future neural network models for sentiment analysis could be generating sentiment polarity prediction of documents using aggregation of predictions on smaller excerpt of the entire text.
File in questo prodotto:
File Dimensione Formato  
ErionCanoDTA.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 758.81 kB
Formato Adobe PDF
758.81 kB Adobe PDF Visualizza/Apri
10-1108_DTA-03-2018-0017.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 824.42 kB
Formato Adobe PDF
824.42 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
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/11583/2710070
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo