结合情感词典的主动贝叶斯文本情感分类方法

提出一种改进的结合情感词典的主动贝叶斯情感分类方法(SLAB).为了证明提出方法的有效性,选用康奈尔影评数据集和互联网电影资料库(IMDB)数据集作为实验数据,并与基于不确定性采样策略的主动学习方法进行比较.结果表明:文中提出的方法在较少的标注训练集下,能够取得更高的分类准确率,一定程度上解决了基于不确定性采样策略的主动学习方法中的误差累积问题.

Text Sentiment Classification Based on Semantic Lexicon and Active Bayesian

An improved sentiment classification method combined semantic lexicon and active Bayesian(SLAB)is proposed. To demonstrate the effectiveness of our proposed method, the Cornell movie review datasets and Internet movie database(IMDB)datasets are exploited as our experimental data and the active learning method based on the uncertainty of sampling is studied as a comparison. The results show that the proposed method can achieve higher classification accuracy with less labeled training set, which alleviates the influence of error accumulation caused by the active learning method based on the uncertainty of sampling.