POSpart of speech METHODS FOR PERFORMING SENTIMENT ANALYSIS OF MESSAGES IN SOCIAL NETWORK SERVICE BASED ON PART OF SPEECH FEATURE AND SENTIMENT ANALYSIS APPARATUS FOR PERFORMING THE SAME

摘要

The emotion analysis method based on the POS feature performed by the emotion analysis device for emotion analysis of a social network service (SNS) message includes: selecting at least one sentence of sentences in the SNS message as a training data set, and the selected training data Of the sentences in the set, the sentences that are not related or related to the emotional feature based on the emotional feature are removed from the training data set, and the POS tagging rules include words in the sentences included in the training data set. Tagging according to grouping into a feature set, assigning weights to words in a sentence included in the selected training dataset based on the dependency of the grouped feature set, and And grouping sentences included in the training dataset into classes having at least two polarities, positive and negative, wherein the sentences included in the training dataset are classified into positive and negative sentences according to the polarity. do.