SENTIMENT CLASSIFICATION DEVICE BASED ON NATURAL LANGUAGE PROCESSING SENTIMENT CLASSIFICATION METHOD BASED ON NATURAL LANGUAGE PROCESSING AND PROGRAM STORED IN A RECORDING MEDIUM

According to an embodiment of the present invention, provided is a sentiment classification device based on natural language processing, comprising: a data crawling part for collecting a plurality of sample text data related to an input keyword; a classification label storage part for storing sentim...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: BYEON HAE WON, YUN SANG HYUN, EOM GA YEONG
Format: Patent
Sprache:eng ; kor
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:According to an embodiment of the present invention, provided is a sentiment classification device based on natural language processing, comprising: a data crawling part for collecting a plurality of sample text data related to an input keyword; a classification label storage part for storing sentiment classification labels that classify the plurality of collected sample text data into two or more sentiments; a prediction model construction part for constructing a sentiment prediction model using a learning model for the plurality of sample text data and sentiment classification labels; and a sentiment classification part for performing sentiment classification on text data to be analyzed using the constructed sentiment prediction model and providing the probability value of classification accuracy. Therefore, provided are a sentiment classification device based on natural language processing, a sentiment classification method based on natural language processing and a program, wherein information related to the public opinion can be provided accurately. 본 발명의 일 실시예에 의하면, 입력 키워드와 관련된 복수의 샘플 텍스트 데이터를 수집하는 데이터 크롤링부; 수집된 복수의 샘플 텍스트 데이터를 2 이상의 감성(sentiment)으로 분류한 감성 분류 레이블을 저장하는 분류 레이블 저장부; 복수의 샘플 텍스트 데이터 및 감성 분류 레이블에 대하여 학습 모델을 이용하여 감성 예측 모델을 구축하는 예측 모델 구축부; 및 구축된 감성 예측 모델을 이용하여 분석 대상의 텍스트 데이터에 대하여 감성 분류를 수행하고, 분류 정확도 확률값을 제공하는 감성 분류부를 포함하는 자연어 처리 기반의 감성 분류 장치가 제공될 수 있다.