Analysis of Emotional Tendency Based on Chinese Sugar-water Shop Evaluation Text

Abstract

The catering market has developed rapidly, and under the influence of the Internet and the epidemic, online consumption has become increasingly strong. Food is the life of the people, and sweets are an important factor in improving happiness in life. For the sugar water store, combined with online and offline fine operation, grasp the user evaluation, in order to stand out in the competition. This research uses the evaluation data of the eight sugar water shops in Guangzhou to extract keywords using TextRank for the texts with long evaluation data, so that the evaluation texts are controlled within 200 words, and then machine learning algorithms are used to analyze, mine and classify them. The experimental results show that this method can solve the binary classification problem of positive emotion and negative emotion in short time.