A Study on Methods of Automatic Extraction of Korean-Language Modification Relationships for Sentiment analysis

Abstract

The most of sentiment analysis on the user reviews only aim to classify the review as overall positive, negative, and neutral sentiment in terms of the overall polarity score. Such overall sentiment score cannot provide detailed information. This study proposes a method of automatic extraction of features and their modifying sentiment words in user reviews, thus a recommendation system provide more detailed sentiment and information. To parse such sentiment and information, we propose a general method for extracting modification relations between nouns and adjectives in Korean sentences, which are corresponding to features and their modifying (sentiment) words, respectively.