Sentence sentiment classification system and method based on sentiment dictionary construction by the price fluctuation and convolutional neural network

摘要

The present invention relates to a system for building an emotion dictionary in accordance with price fluctuations and classifying sentence emotions based on a convolutional neural network and a method thereof. According to the present invention, the system includes a data preprocessing part, an emotion dictionary building part and an emotion classification part. The data preprocessing part analyzes a morpheme by extracting a sentence from a document group and processes a stop-word by removing a discrimination-less word from the document group. The emotion dictionary building part extracts and expresses a word as a vector based on internal/external border values of the word to identify the frequency and meaning of the word in the document group, collects price fluctuation information in accordance with a specific field, and creates an emotion dictionary by classifying the affirmation and negation of the word based on the price fluctuation information. The emotion classification part classifies the emotion of a sentence by using a convolutional neural network (CNN) based on the emotion dictionary.