Unsupervised acquisition of domain aspect terms for Aspect Based Opinion Mining

@Article {
author = {Aitor García, Montse Cuadros, German Rigau, Seán Gaines},
title = {Unsupervised acquisition of domain aspect terms for Aspect Based Opinion Mining},
journal = {Sociedad Española de Procesamiento del Lenguaje Natural},
pages = {121-128},
volume = {53},
keywds = {

aspect based sentiment analysis, unsupervised lexicon generation

}
abstract = {

The automatic analysis of opinions, which usually receives the name of opinion mining or sentiment analysis, has gained a great importance during the last decade. This is mainly due to the overgrown of online content in the Internet. The so-called aspect based opinion mining systems aim to detect the sentiment at “aspect” level (i.e. the precise feature being opinionated in a clause or sentence). In order to detect such aspects it is required some knowledge about the domain under analysis. The vocabulary in different domains may vary, and different words are interesting features in different domains. We aim to generate a list of domain related words and expressions from unlabeled domain texts, in a completely unsupervised way, as a first step to a more complex opinion mining system.

}
date = {2014-09-19},
year = {2014},
}