Chinese Micro-Blog Sentiment Analysis Based on Multiple Sentiment Dictionaries and Semantic Rule Sets

Jiesheng Wu,Kui Lu,Shuzhi Su,Shibing Wang

doi:10.1109/access.2019.2960655

Abstract

Sentiment analysis of Chinese micro-blog based on sentiment dictionary has become a challenging research subject in the field of artificial intelligence. However, due to insufficient sentiment words, Chinese micro-blog sentiment analysis is difficult to process high accuracy. Aimed at this issue, we propose a method for constructing multiple sentiment dictionaries, which mainly constructs original sentiment dictionary, emoji dictionary, and other related dictionaries. Among them, we have innovatively constructed a Chinese micro-blog new word sentiment dictionary. Multiple sentiment dictionaries increase the coverage of sentiment words. At the same time, we further analyze semantic rule sets between Chinese micro-blog texts and take the inter-sentence analysis rules and sentence pattern analysis rules into the sentiment analysis of Chinese micro-blog, which further improves the accuracy of Chinese micro-blog sentiment analysis. Finally, based on the method of multiple sentiment dictionaries and semantic rule sets, we propose an algorithm for Chinese micro-blog sentiment calculation from complex sentences to clauses and then from clauses to words, and finally combined with the emoji. This algorithm can accurately classify Chinese micro-blog into positive Chinese micro-blog, negative Chinese micro-blog, and neutral Chinese micro-blog. The experimental results show that this method has greatly improved the sentiment analysis of Chinese micro-blog.

Highlights

With the popularity of the mobile Internet in recent years, Chinese micro-blog has become a new social media platform for the public, which has become a social tool that people use every day
The subjective Chinese micro-blog news published by these people involves all aspects of life, which contains rich sentiment information
SENTIMENT ANALYSIS OF THE SEMANTIC RULE SETS The main part of Chinese micro-blog is text, which is composed of Chinese characters, and there are certain grammatical relations and semantic rules between the texts

Summary

INTRODUCTION

With the popularity of the mobile Internet in recent years, Chinese micro-blog has become a new social media platform for the public, which has become a social tool that people use every day. This paper proposes a method based on multiple sentiment dictionaries and semantic rule sets to analyze Chinese micro-blog. Combined with the semantic rule sets between the Chinese micro-blog texts to calculate the sentiment value, according to the magnitude of the sentiment. J. Wu et al.: Chinese Micro-Blog Sentiment Analysis Based on Multiple Sentiment Dictionaries and Semantic Rule Sets. The contributions of this method mainly consist of the following three aspects: A. B. ANALYSIS OF SEMANTIC RULE SETS Chinese micro-blogs are mainly composed of Chinese texts except for a few elements such as emojis. The sentiment analysis of Chinese micro-blog will be carried out in order from the above three aspects, and the argument analysis will be given in combination with the experiment

RELATED WORKS

SENTIMENT ANALYSIS OF THE SEMANTIC RULE SETS

Findings

CONCLUSION