计算机与数字工程2019，Vol.47Issue(2)：281-284,303,5.DOI:10.3969/j.issn.1672-9722.2019.02.005
基于词向量的文本分类研究
Research on Text Classification Based on Word Embedding
摘要
Abstract
Focusing on the problems of the low classification accuracy of traditional feature selection algorithm,an improved text feature selection algorithm is proposed based on word vector. The article takes microblog data as the research object to carry on the sentiment analysis. It forwards an assumption that the feature items which are similar to the ones have strong category distinguish ability,would also have strong ability to distinguish categories. It applies word embedding which Word2vec trains to the process of traditional feature selection,and expands the feature items appropriately according to the similarity relation between the word vec?tors.The experimental results show that the improved feature selection algorithm has better results in its classification accuracy.关键词
词向量/特征扩展/Word2vec/文本分类Key words
word embedding/feature expansion/Word2vec/text classification分类
信息技术与安全科学引用本文复制引用
马力,李沙沙..基于词向量的文本分类研究[J].计算机与数字工程,2019,47(2):281-284,303,5.
