Title :
The study of sentiment analysis on Chinese comment texts
Author :
Lizhen Liu ; Hao Liu ; Hanshi Wang ; Wei Song ; Jingli Lu
Author_Institution :
Inf. & Eng. Coll., Capital Normal Univ., Beijing, China
Abstract :
As known to all, a word´s implication could differ in different domain, even the same word in the same domain may indicate diverse polarity with respect to different aspects. Due to the domain-dependent characteristic of some words, it is difficult to build a generally used sentiment lexicon. At the same time, there are a large amount of terms whose polarity is always definite. For example, “excellent” and “bad” respectively represent determinate polarity of “positive” and “negative”. In this paper, we construct a sentiment lexicon making use of both the context-dependent and the context-independent features. The traits of the semi-structured product reviews offered by users are also used in the construction process. At last, we put forward a method of combining the domain-specific lexicon and the existing sentiment wordlist such as “Hownet” for sentiment analysis.
Keywords :
natural language processing; text analysis; Chinese comment texts; Hownet; construction process; context-dependent feature; context-independent feature; domain-dependent characteristic; domain-specific lexicon; semistructured product reviews; sentiment analysis; sentiment lexicon; sentiment wordlist; Buildings; Data mining; Semantics; Sentiment analysis; Statistical analysis; Thesauri; context-sensitive sentiment lexicon; polarity classification; sentiment analysis;
Conference_Titel :
Software Engineering and Service Science (ICSESS), 2014 5th IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4799-3278-8
DOI :
10.1109/ICSESS.2014.6933591