摘要
针对旅游网络评价使用的旅游情感词汇量不多的特点,提出一种基于旅游情感词典和机器学习相结合的方法,用于旅游网络点评的情感倾向性分析研究。采用向量空间模型表示旅游评价文本,使用旅游情感词典对特征空间进行降维,采用TF-IDF特征权重法计算权重,利用SVM机器学习模型对评价进行分类,实验结果表明,该方法能够有效地进行旅游网络评价分类。
This paper provides an approach for sentiment analysis of tourism reviews through Internet service by combining semantic lexicon with machine learning.The approach expresses tourism reviews by adopting Vector Space Model(VSM).It reduces dimension of feature space by semantic lexicon.The weights are calculated by term frequency-inverse document frequency(TF-IDF).The tourism reviews are classified by Support Vector Machine(SVM).Experimental results show that the proposed approach can make sentiment classification for plenty of tourism reviews efficiently.
出处
《计算机与数字工程》
2016年第4期578-582,766,共6页
Computer & Digital Engineering
基金
南京旅游职业学院基金项目(2015YKT10)
大数据时代旅游数据挖掘与应用研究资助
关键词
机器学习
情感词典
情感分析
machine learning
semantic lexicon
sentiment analysis