计算机应用与软件2017，Vol.34Issue(3)：27-30,80,5.DOI:10.3969/j.issn.1000-386x.2017.03.005
一种利用语义相似特征提升细粒度情感分析方法
A FINE-GRAINED SENTIMENT ANALYSIS METHOD USING SEMANTIC SIMILARITY FEATURE
摘要
Abstract
Sentiment analysis mainly focuses on the study of people's emotional expressions including positive and negative sentiment.With the explosive growth of web texts, sentiment analysis has become a hot topic in both academic researches and practical applications.The method of fine-grained sentiment analysis traditionally adopts a 2-step strategy, which is extremely easy to result in stack-up bottom-up errors.A joint fine-grained sentiment analysis framework based on Markov logic is proposed to solve this problem."Bottom-up" and "Top-down" are the two most commonly used traditional overall features.In order to improve the joint learning ability of fine-grained sentiment analysis, a new semantic similarity feature has been proposed.Experiments on the data set of Chinese sentiment analysis prove that the semantic similarity feature can bring a significant improvement to the joint fine-grained sentiment analysis framework.关键词
细粒度的情感分析/马尔科夫逻辑/语义相似特征Key words
Fine-grained sentiment analysis/Markov logic/Semantic similarity feature分类
信息技术与安全科学引用本文复制引用
陈自岩,黄宇,王洋,傅兴玉,付琨..一种利用语义相似特征提升细粒度情感分析方法[J].计算机应用与软件,2017,34(3):27-30,80,5.基金项目
国家自然科学基金项目(61331017). （61331017）
