A Lightweight Sentiment Analysis Method

A Lightweight Sentiment Analysis Method

YU Qingshuang1 , ZHOU Jie2, and GONG Wenjuan1

(1. China University of Petroleum (East China), Qingdao, Shandong 266000, China;
2. Operation Coordination Department of Tianjin Branch of CNOOC (China) Co., Ltd., Tianjin 300000, China)

Abstract：The emergence of big data leads to an increasing demand for data processing methods. As the most influential media for Chinese domestic film ratings, Douban contains a huge amount of data, and one can understand users’ perspectives towards these movies by analyzing these data. In this article, we study film’s critics from the Douban website, perform sentiment analysis on the data obtained by crawling, and visualize the results with a word cloud. We propose a lightweight sentiment analysis method which is free from heavy training and visualize the results in a more conceivable way.
Keywords:web crawler; microblog; text sentiment analysis; word cloud