Aspect-based Sentiment Analysis: Information Extraction and Applications for Portuguese texts

• Grant number: 12/16131-4
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: September 01, 2013
• End date: February 29, 2016
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Thiago Alexandre Salgueiro Pardo
• Grantee: Pedro Paulo Balage Filho
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

Sentiment Analysis is a recent area of Natural Language Processing (NLP) which aims to process texts with opinion, sentiment and subjectivity (Pang and Liu, 2008). In this area, there are three levels of analysis for the sentiment present in the text: text level, sentence level and aspect or entity level. In the aspect-based sentiment analysis, feelings are extracted according to the aspects they modify. The focus of this work is on the aspect-based sentiment extraction. The aim of this work is to produce open-source tools and techniques to transform opinion texts from the unstructured natural language into a structured data likely to be manipulated by other systems. A consequence of this aim is the use of these techniques to help other activities in NLP, such as opinion-oriented automatic summarization, question answering, recommendation systems, among others. The contributions of this work aim to address the lack of systems for the Portuguese language while encourage the use of extracted sentiments to the improvement other activities in NLP.

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

BALAGE FILHO, Pedro Paulo. Aspect extraction in sentiment analysis for portuguese language. 2017. Doctoral Thesis - Universidade de São Paulo (USP). Instituto de Ciências Matemáticas e de Computação (ICMC/SB) São Carlos.