面向延安景点评论的情感词典构建

Construction of emotional dictionary for Yan’an scenic spot review

景区评论中蕴含着丰富的情感内涵,如何挖掘出有价值的信息逐渐成为研究人员关注的焦点。运用TF-IDF算法和SO-PMI算法构建了面向延安景点评论的情感词典。实验结果表明,本文所构建的情感词典在情感分类方面准确率达到了89%,召回率以及F1值都有明显提升,从而验证了该词典的有效性和可行性。

Comments on scenic spots contain rich emotional connotations,and how to detect valuable information in these comments is drawing much researchers’attention.In this paper,TF-IDF algorithm and SO-PMI algorithm are used to compile an emotion dictionary for Yan’an scenic spot reviews.Experiments show that the accuracy rate of emotion classification of this dictionary is 89%,and the recall rate and F1 value are notably improved,which verifies the effectiveness and feasibility of this dictionary.