面向旅游在线评论情感词典构建方法

旅游在线评论情感分析的基础是情感词典的构建。在领域情感词典构建过程中，通常仅使用词频作为筛选种子词集的标准，而并未考虑其内部词语的关联程度，这会导致种子词集聚类效果不明显，进而影响情感词语归类精度。因此，基于词向量模型，提出一种情感词典种子词集筛选方法。该方法将情感词语以向量形式表征并计算词向量间距离，形成种子词集的筛选标准和分类依据，再通过类别判断形成在线评论的情感词典。最后，构建了山岳型旅游景区在线评论情感词典，并通过对比实验验证了方法的有效性，对提高情感词语归类精度和旅游在线评论情感词典的构建起到了积极的作用。

Construction method of sentiment lexicon for online travel reviews

The basis of emotional analysis for the online travel reviews is the construction of the sentiment lexicon. In the traditional process of constructing the field emotional dictionary, the word frequency is usually used as the criterion of screening the seed word set, instead of the association degrees of the internal words, which will lead to the effect of the seed word set clustering not that obvious, thus affecting the emotional word classification accuracy. Therefore, this paper proposed a method of seed word collection based on word vector, which expressed the emotional words in vector form and calculate the distance between word vectors as a selection criteria and classification basis of the seed word set. Finally, the emotional dictionary of the mountain scenic area was constructed, and the validity of the method is verified by a series of comparison experiments. This paper plays a positive role in improving the accuracy of emotional words and the construction of sentiment lexicon on tourism online travel reviews.