摘要
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。
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,it constructed the emotional dictionary of the mountain scenic area,and verifies the validity of the method 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.
引文
[1]胡兴报,苏勤.黄山国内旅游者网络旅游信息搜索行为研究[J].安徽师范大学学报:自然科学版,2011,34(3):282-287.(Hu Xingbao,Su Qin. Research on domestic tourist online tourism information searching behavior in Huangshan city[J]. Journal of Anhui Normal University:Natural Science Edition,2011,34(3):282-287.)
[2]中国互联网络信息中心(CNNIC). 2016年第38次《中国互联网络发展状况统计报告》[R]. 2016.(China Internet Information Center(CNNIC). The 38th Statistical Report on the Development of China Internet in 2016[R]. 2016.)
[3]许晖,许守任,王睿智.消费者旅游感知风险维度识别及差异分析[J].旅游学刊,2013,28(12):71-80.(Xu Hui,Xu Shouren,Wang Ruizhi. Study on dimension identification and variance analysis of consumers’perceived risk in travel[J]. Tourism Tribune,2013,28(12):71-80.
[4] Andreevskaia A,Bergler S. Mining Word Net for a fuzzy sentiment:sentiment tag extraction from wordnet glosses[C]//Proc of Conference of the European Chapter of the Association for Computational Linguistics. 2006.
[5] Baccianella S,Esuli A,Sebastiani F. SentiWordNet 3. 0:an enhanced lexical resource for sentiment analysis and opinion mining[C]//Proc of International Conference on Language Resources and Evaluation. 2010:83-90.
[6] Turney P D. Thumbs up or thumbs down?:semantic orientation applied to unsupervised classification of reviews[C]//Proc of Annual Meeting of the Association for Computational Linguistics. 2002:417-424.
[7] Wang G,Araki K. Modifying SO-PMI for Japanese Weblog opinion mining by using a balancing factor and detecting neutral expressions[C]//Proc of Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics.2007:189-192.
[8] Yang Aimin,Lin Jianghao,Zhou Yongmei,et al. Research on building a Chinese sentiment lexicon based on SO-PMI[J]. Applied Mechanics&Materials,2013,263-266:1688-1693.
[9]柳位平,朱艳辉,栗春亮,等.中文基础情感词词典构建方法研究[J].计算机应用,2009,29(10):2875-2877.(Liu Weiping,Zhu Yanhui,Li Chunliang,et al. Research on building Chinese basic semantic lexicon[J]. Computer Application,2009,29(10):2875-2877.)
[10]桂斌,杨小平,张中夏,等.基于微博表情符号的情感词典构建研究[J].北京理工大学学报,2014,34(5):537-541.(Gui Bin,Yang Xiaoping,Zhang Zhongxia,et al. Research on building lexicon for sentiment analysis based on the Chinese microblogging smiley[J]. Journal of Beijing University of Technology,2014,34(5):537-541.)
[11]周咏梅,阳爱民,杨佳能.一种新闻评论情感词典的构建方法[J].计算机科学,2014,41(8):67-69.(Zhou Yongmei,Yang Aimin,Yang Jianeng. Construction method of sentiment lexicon for news reviews[J]. Computer Science,2014,41(8):67-69.)
[12]郭顺利,张向先.面向中文图书评论的情感词典构建方法研究[J].现代图书情报技术,2016,32(2):67-74.(Guo Shunli,Zhang Xiangxian. Research on the construction method of emotional dictionary for Chinese book reviews[J]. Modern Library and Information Technology,2016,32(2):67-74.)
[13]徐琳宏,林鸿飞,潘宇,等.情感词汇本体的构造[J].情报学报,2008,27(2):180-185.(Xu Linhong,Lin Hongfei,Pan Yu,et al.Constructing the affective lexicon ontology[J]. Journal of the China Society for Scientific and Technical Information,2008,27(2):180-185.)
[14]Mikolov T,Chen Kai,Corrado G,et al. Efficient estimation of word representations in vector space[EB/OL]. 2013-01-16. https://arxiv.org/abs/1301. 3781.
[15]Giatsoglou M,Vozalis M G,Diamantaras K,et al. Sentiment analysis leveraging emotions and word embeddings[J]. Expert Systems with Applications,2017,69(3):214-224.
[16]Yuan Y,He L,Peng L,et al. A new study based on word2vec and cluster for document categorization[J]. Journal of Computational Information Systems,2014,10(21):9301-9308.
[17]Xue Bai,Fu Chen,Zhan Shaobin. A study on sentiment computing and classification of Sina Weibo with word2vec[C]//Proc of IEEE International Congress on Big Data. Piscataway,NJ:IEEE Press,2014:358-363.
[18]朱嫣岚,闵锦,周雅倩,等.基于How Net的词汇语义倾向计算[J].中文信息学报,2006,20(1):16-22.(Zhu Yanlan,Min Jin,Zhou Yaqian,et al. Semantic orientation computing based on How Net[J].Chinese Journal of Information Science,2006,20(1):16-22.)
[19]杜锐.面向中文微博文本的情感分类研究[D].株洲:湖南工业大学,2014.(Du Rui. Emotional classification for Chinese Weibo texts[D]. Zhuzhou:Hunan University of Technology,2014.)