基于情感时序距离和转折同化的文本情感分类-计算机工程与应用.PDFVIP

158 2018 ，54（14） Computer Engineering and Applications 计算机工程与应用 基于情感时序距离和转折同化的文本情感分类 用 郑 诚，谈小雨，于秀开，曹 杨 应 ZHENG Cheng, TAN Xiaoyu, YU Xiukai, CAO Yang 与 安徽大学 计算机科学与技术学院，合肥 230601 程 School of Computer Science and Technology, Anhui University, Hefei 230601, China g 工 r o ZHENG Cheng, TAN Xiaoyu, YU Xiukai, et al. Text sentiment classification based on sentiment series distance and . j turning assimilation. Computer Engineering and Applications, 2018, 54 （14）：158-162. 机 a 算 e Abstract ：Considering the overall texts orientation identification of Chinese emotional texts and their sentiment express c . sequence have a great connection, and for the emotional texts, emotion tendency expression which is closer to the end of 计 w the texts is more influential to identify whole texts orientation. Therefore, for the short texts which express emotion incon- spicuously or complicatedly, this paper considers the sequence of the appearance of the emotional nodes in the text and w the sentiment assimilation of the turning point to classify the emotional texts more efficiently. The experimental result on w the emotional texts dataset crawled from a shopping site shows that the classification method proposed in this paper is sig- nificantly better than the support vector machine classifier that is based on word features simply. Key words ：text sentiment classification; Support Vector Machine （SVM）; sentiment distance; turning assimilation 摘 要：考虑到中文评价文本的整体情感倾向性与其表达的情感顺