Inicio  /  Information  /  Vol: 11 Par: 9 (2020)  /  Artículo
ARTÍCULO
TITULO

Evaluating Richer Features and Varied Machine Learning Models for Subjectivity Classification of Book Review Sentences in Portuguese

Luana Balador Belisário    
Luiz Gabriel Ferreira and Thiago Alexandre Salgueiro Pardo    

Resumen

Texts published on social media have been a valuable source of information for companies and users, as the analysis of this data helps improving/selecting products and services of interest. Due to the huge amount of data, techniques for automatically analyzing user opinions are necessary. The research field that investigates these techniques is called sentiment analysis. This paper focuses specifically on the task of subjectivity classification, which aims to predict whether a text passage conveys an opinion. We report the study and comparison of machine learning methods of different paradigms to perform subjectivity classification of book review sentences in Portuguese, which have shown to be a challenging domain in the area. Specifically, we explore richer features for the task, using several lexical, centrality-based and discourse features. We show the contributions of the different feature sets and evidence that the combination of lexical, centrality-based and discourse features produce better results than any of the feature sets individually. Additionally, by analyzing the achieved results and the acquired knowledge by some symbolic machine learning methods, we show that some discourse relations may clearly signal subjectivity. Our corpus annotation also reveals some distinctive discourse structuring patterns for sentence subjectivity.

 Artículos similares

       
 
Marko Keskinen and Olli Varis    
The water-energy-food nexus (?nexus?) is promoted as an approach to look at the linkages between water, energy and food. The articles of Water?s Special Issue ?Water-Energy-Food Nexus in Large Asian River Basins? look at the applicability of the nexus ap... ver más
Revista: Water

 
Mohammad Salih Memon, Mushtaque Ali Jariko, Tania Mushtaque, Munir Ahmed Ahmadani, Faiz Muhammad Shaikh, Syed Abdul Sattar Shah     Pág. 2275 - 2282
The current research investigates the practices and understanding of Corporate Social Responsibility (CSR) in public sector of Pakistan. CSR is becoming very familiar in the field of business and is getting much popularity among scholars, academicians, p... ver más

 
Alberto Asquer    
In sub-national governments, elected public officers can exercise considerable influence on the regulation of local water services, in such ways as, for example, contributing to the design of local regulatory institutions, to the formulation of tariff ru... ver más
Revista: Water

 
John T. Murphy, Jonathan Ozik, Nicholson T. Collier, Mark Altaweel, Richard B. Lammers, Andrew Kliskey, Lilian Alessa, Drew Cason and Paula Williams    
Natural language processing (NLP) and named entity recognition (NER) techniques are applied to collections of newspaper articles from four cities in the U.S. Southwest. The results are used to generate a network of water management institutions that refl... ver más
Revista: Water

 
Edivanio Duarte de Souza,Eduardo José Wense Dias    
Parte considerável dos estudos epistemológicos no campo da ciência da informação, no Brasil, tem como vetor a interdisciplinaridade. Contudo, alguns denunciam a dificuldade nos processos de integração disciplinar e de consolidação epistemológica. Eles tê... ver más