基于大数据的旅游目的地情感评价方法探究

doi:10.11821/dlyj201706008

摘要/Abstract

摘要：

基于情绪分类取向,通过界定三个旅游文本情感分析的过滤参数：旅游专属词库、语义逻辑规则和情感乘数,构建基于网络大数据的旅游目的地情感评价模型。基于该模型,抓取了120731条游客评论对8个旅游目的地进行评价,并以联合国世界旅游组织旅游可持续发展监测数据作为标准数据进行校验。研究证实三个过滤参数具有一定的科学性,能够较为准确地捕捉到游客对目的地评价的总体情感意象;经过单年度和多年度校验,六类规则的准确度依次为：C2>C1>C3>B>评分法>A,即规则C2下的评价结果与监测结果最为吻合。结论证实了旅游大数据的可用性,为后续的理论推进和实践应用提供了科学依据。

关键词: 大数据, 旅游目的地, 情感评价模型, 情感意象

Abstract:

The contemporary studies of tourism big data are not sufficient to utilize online tourist-generated contents for evaluating tourism destinations, while the content-analysis studies in linguistic studies have yet to have qualified technics for conducting tourism research. In order to bridge this gap between these, this paper constructs an emotion model for evaluating tourism destinations based on tourists' online reviews. This model is composed of three emotional filtering factors including tourism lexicon, grammatical logics and emotional multipliers. The tourism lexicon contains 3507 positive emotional words and 3365 negative emotional words. It is used to depict the general emotional image of a tourist online review by calculating positive and negative words within the review. Every emotional word will be counted as one score, either positive or negative. Grammatical logics contain 13 rules which adjust the positive or negative scores and give the final emotional score of the review. Emotional multiplier in this study is set from three to five. It is used to correct the deviation of exaggerated positive emotions due to the existing pro-positive preference in human emotional expression. This paper collects 120731 pieces of tourists' online reviews among eight tourist destinations (Yangshuo, Zhangjiajie, Huangshan, Chengdu, Luoyang, Kanas, Jiaozuo and Xishuangbanna) and uses this model to evaluate the overall emotional images of these destinations. The result is compared to the questionnaire-based survey data conducted by UNWTO (United Nation, World Tourism Organization) among these destinations from 2013 to 2015. The verification proves that the three emotional filtering factors are effective in mapping emotional images of tourists' online reviews. Based on both single and multiple-year verification, the accuracy of the proposed six sub-models is ranged from high to low as follows: C2>C1>C3>B>Direct Scores>A. This outcome means that the model-based result is the closest to the UNWTO result under the C2 that emotional multiplier is set at 4 and the tourism lexicon and grammatical logics are applied. This paper contributes to the literature by paving alternative ways of destination evaluation and proves the usefulness of tourism big data in geographical studies. This effort will underpin subsequent theoretical and empirical studies in tourism geography.

Key words: big data, tourism destination, emotional evaluation model, emotional image

刘逸, 保继刚, 朱毅玲. 基于大数据的旅游目的地情感评价方法探究[J]. 地理研究, 2017, 36(6): 1091-1105.

Yi LIU, Jigang BAO, Yiling ZHU. Exploring emotion methods of tourism destination evaluation: A big-data approach[J]. GEOGRAPHICAL RESEARCH, 2017, 36(6): 1091-1105.

图/表 6

图1

表1

表2

表3

表4

表5

参考文献 50

[36]	[Wu Xiaogen, Du Yingying.Empirical study on perceptive image formation of tourists on tourism destination: A case study of Nantong, Jiangsu province. Geographical Research, 2011, 30(9): 1554-1565.] doi: 10.11821/yj2011090002
[37]	Rojas C D, Camarero C.Visitors' experience, mood and satisfaction in a heritage context: Evidence from an interpretation center. Tourism Management, 2008, 29(3): 525-537. doi: 10.1016/j.tourman.2007.06.004
[38]	贾衍菊, 林德荣. 旅游者服务感知、地方依恋与忠诚度: 以厦门为例. 地理研究, 2016, 35(2): 390-400. doi: 10.11821/dlyj201602015
	[Jia Yanju, Lin Derong.Tourists' perception of urban service, place attachment and loyal behaviors: A case study of Xiamen. Geographical Research, 2016, 35(2): 390-400.] doi: 10.11821/dlyj201602015
[39]	Chen C, Chen F.Experience quality, perceived value, satisfaction and behavioral intentions for heritage tourists. Tourism Management, 2010, 31(1): 29-35. doi: 10.1016/j.tourman.2009.02.008
[40]	Radojevic T, Stanisic N, Stanic N.Ensuring positive feedback: Factors that influence customer satisfaction in the contemporary hospitality industry. Tourism Management, 2015, 51(12): 13-21.
[41]	Qiu L, Lin H, Leung A K, et al.Putting their best foot forward: Emotional disclosure on Facebook. CyberPsychology, Behavior & Social Networking, 2012, 15(10): 569-572.
[42]	徐琳宏, 林鸿飞, 杨志豪. 基于语义理解的文本倾向性识别机制. 中文信息学报, 2007, 21(1): 96-100. doi: 10.3969/j.issn.1003-0077.2007.01.016
	[Xu Linhong, Lin Hongfei, Yang Zhihao.Text orientation identification based on semantic comprehension. Journal of Chinese Information Processing, 2007, 21(1): 96-100.] doi: 10.3969/j.issn.1003-0077.2007.01.016
[43]	周小兵. 论现代汉语的程度副词. 中国语文, 1995, 20(2): 100-104.
	[Zhou Xiaobing.The theory on the adverbs of degree in contemporary Chinese. Studies of the Chinese Language, 1995, 20(2): 100-104.]
[44]	蔺璜, 郭姝慧. 程度副词的特点范围与分类. 山西大学学报: 哲学社会科学版, 2003, 26(2): 71-74. doi: 10.3969/j.issn.1000-5935.2003.02.015
	[Lin Huang, Guo Shuhui.On the characteristics, range and classification of adverbs of degree. Journal of Shanxi University: Philosophy & Social Science, 2003, 26(2): 71-74.] doi: 10.3969/j.issn.1000-5935.2003.02.015
[45]	邸鹏, 李爱萍, 段利国. 基于转折句式的文本情感倾向性分析. 计算机工程与设计, 2014, 35(12): 4289-4295. doi: 10.3969/j.issn.1000-7024.2014.12.045
	[Di Peng, Li Aiping, Duan Liguo.Text sentiment polarity analysis based on transition sentence. Computer Engineering and Design, 2014, 35(12): 4289-4295.] doi: 10.3969/j.issn.1000-7024.2014.12.045
[46]	吕淑湘. 疑问·否定·肯定. 中国语文, 1985, 4(2): 41-43.
	[Lv Shuxiang.Question, negative, positive. Studies of the Chinese Language, 1985, 4(2): 41-43.]
[47]	李泉. 汉语语法考察与分析. 北京: 北京语言文化大学出版社, 2001.
	[Li Quan.The Investigation and Analysis of Grammar in Chinese Language. Beijing: Beijing Language &Culture University Press, 2001.]
[48]	程晓明. 转折句式与转折词. 湖北民族学院学报: 社会科学版, 1998, 16(4): 36-40.
	[Cheng Xiaoming.Transition sentence and advertise. Journal of Hubei Institute for Nationalities: Social Science Edition, 1998, 16(4): 36-40.]
[49]	胡裕树, 许宝华. 現代汉语. 上海:上海教育出版社, 1981.
[1]	Schmallegger D, Carson D.Destination image projection on consumer-generated content websites: A case study of the Flinders Ranges. Information Technology & Tourism, 2009, 11(2): 111-127. doi: 10.3727/109830509789994838
[2]	张文, 顿雪霏. 探讨大陆游客对台湾旅游目的地形象的感知: 基于网上游记的内容分析. 北京第二外国语学院学报, 2010, (11): 75-83. doi: 10.3969/j.issn.1003-6539.2010.11.011
[49]	[Hu Yushu, Xu Baohua. Contemporary Chinese.Shanghai: Shanghai Education Press, 1981.]
[50]	刘永红. 转折复句语意重心的逻辑语义分析. 暨南大学华文学院学报, 2003, 8(1): 45-52. doi: 10.3969/j.issn.1674-8174.2003.01.007
[2]	[Zhang Wen, Dun Xuefei.Study on image perception of mainland tourists to Taiwan: Based on content analysis of online travels. Journal of Beijing International Studies University, 2010, (11): 75-83.] doi: 10.3969/j.issn.1003-6539.2010.11.011
[3]	张珍珍, 李君轶. 旅游形象研究中问卷调查和网络文本数据的对比: 以西安旅游形象感知研究为例. 旅游科学, 2014, 28(6): 73-81. doi: 10.3969/j.issn.1006-575X.2014.06.007
	[Zhang Zhenzhen, Li Junyi.A comparative study on the data of a questionnaire and web texts in tourism image researches: A case study of Xi'an's tourism image perception. Tourism Science, 2014, 28(6): 73-81.] doi: 10.3969/j.issn.1006-575X.2014.06.007
[4]	Bulchand Gidumal J, Melián González S, Lopez Valcarcel B G. A social media analysis of the contribution of destinations to client satisfaction with hotels. International Journal of Hospitality Management, 2013, 35(1): 44-47. doi: 10.1016/j.ijhm.2013.05.003
[5]	Oliver V, Garcia E, Solana A.Big Data and Tourism: New Indicators for Tourism Management. Barcelona: Roca Salvatella and Telefonica, 2014.
[6]	张黎军, 赵霞. 基于大数据分析的旅游管理服务系统. 信息通信, 2014, (11): 232-233. doi: 10.3969/j.issn.1673-1131.2014.11.170
	[Zhang Lijun, Zhao Xia.Tourism management and service system based on big data. Information & Communications, 2014, (11): 232-233.] doi: 10.3969/j.issn.1673-1131.2014.11.170
[7]	吴英鹰. 大数据背景下旅游企业网络营销的创新: 基于AISAS消费者行为分析. 中国商贸, 2013, (12): 107-108.
	[Wu Yingying.The innovation of tourism enterprise network marketing in the big data context: Based on AISAS tourist behavior analysis. China Business & Trade, 2013, (12): 107-108.]
[8]	史春云, 张捷, 沈正平, 等. 旅游目的地竞争力定量评价综述. 人文地理, 2006, 20(3): 72-78.
	[Shi Chunyun, Zhang Jie, Shen Zhengping, et al.An overview of quantitative evaluation of the tourist destination competitiveness. Human Geography, 2006, 20(3): 72-78.]
[9]	钟士恩, 章锦河, 孙晋坤. 基于遗产保护与旅游发展综合评价的古镇型旅游目的地差异化发展路径研究: 以江苏省为例. 地理研究, 2015, 34(7): 1380-1393. doi: 10.11821/dlyj201507016
	[Zhong Shi'en, Zhang Jinhe, Sun Jinshen. The diversified development of historic towns based on the integrated evaluation system of heritage conservation and tourism development in Jiangsu. Geographical Research, 2015, 34(7): 1380-1393.] doi: 10.11821/dlyj201507016
[10]	柴彦威, 塔娜. 中国时空间行为研究进展. 地理科学进展, 2013, 32(9): 1362-1373. doi: 10.11820/dlkxjz.2013.09.006
	[Chai Yanwei, Ta Na.Progress in space-time behavior research in China. Progress in Geography, 2013, 32(9): 1362-1373.] doi: 10.11820/dlkxjz.2013.09.006
[11]	柴彦威, 申悦, 马修军, 等. 北京居民活动与出行行为时空数据采集与管理. 地理研究, 2013, 32(3): 441-451. doi: 10.11821/yj2013030006
	[Chai Yanwei, Shen Yue, Ma Xiujun, et al.The collection and management of space-time data of individual behavior based on location-based technologies: A case study of activity-travel survey in Beijing. Geographical Research, 2013, 32(3): 441-451.] doi: 10.11821/yj2013030006
[12]	柯文前, 俞肇元, 陈伟, 等. 人类时空间行为数据观测体系架构及其关键问题. 地理研究, 2015, 34(2): 373-383. doi: 10.11821/dlyj201502016
	[Ke Wenqian, Yu Zhaoyuan, Chen Wei, et al.Architecture and key issues for human space-time behavior data observation. Geographical Research, 2015, 34(2): 373-383.] doi: 10.11821/dlyj201502016
[13]	甄峰, 王波. “大数据”热潮下人文地理学研究的再思考. 地理研究, 2015, 34(5): 803-811. doi: 10.11821/dlyj201505001
	[Zhen Feng, Wang Bo.Rethinking human geography in the age of big data. Geographical Research, 2015, 34(5): 803-811.] doi: 10.11821/dlyj201505001
[14]	Zheng X, Schwartz Z, Uysal M.What Types of Hotels Make Their Guests (Un)Happy? Text Analytics of Customer Experiences in Online Reviews. Lugano: Springer International Publishing, 2015.
[15]	熊伟, 高阳, 吴必虎. 中外国际高星级连锁酒店服务质量对比研究: 基于网络评价的内容分析. 经济地理, 2012, 32(2): 160-165.
	[Xiong Wei, Gao Yang, Wu Bihu.A comparison research of online commentary about service quality in Sino-foreign international high-rated chain hotels. Economic Geography, 2012, 32(2): 160-165.]
[16]	Ekman P, Friesen W V.Constants across cultures in the face and emotion. Journal of Personality and Social Psychology, 1971, 17(2): 124-129. doi: 10.1037/h0030377 pmid: 5542557
[17]	Mehrabian A, Russell J A.An Approach to Environmental Psychology. Cambridge: The MIT Press, 1974.
[18]	Russell J A.A circumplex model of affect. Journal of Personality and Social Psychology, 1980, 39(6): 1161-1178.
[19]	Cacioppo J T, Gardner W L, Berntson G G.The affect system has parallel and integrative processing components. Journal of Personality & Social Psychology, 1999, 76(5): 839-855.
[20]	乐国安, 董颖红. 情绪的基本结构: 争论、应用及其前瞻. 南开学报: 哲学社会科学版, 2013, 58(1): 140-150.
	[Yue Guo'an, Dong Yinghong. On the categorical and dimensional approaches of the theories of the basic structure of emotions. Nankai Journal: Philosophy, Literature and Social Science Edition, 2013, 58(1): 140-150.]
[21]	Das S R, Chen M Y.Yahoo! For Amazon: Sentiment extraction from small talk on the web. Management Science, 2007, 53(9): 1375-1388. doi: 10.1287/mnsc.1070.0704
[22]	赵妍妍, 秦兵, 刘挺. 文本情感分析. 软件学报, 2010, 21(8): 1834-1848.
	[Zhao Yanyan, Qin Bing, Liu Ting.Sentiment analysis. Journal of Software, 2010, 21(8): 1834-1848.]
[23]	王洪伟, 郑丽娟, 尹裴, 等. 在线评论的情感极性分类研究综述. 情报科学, 2012, 30(8): 1263-1271.
	[Wang Hongwei, Zheng Lijuan, Yin Pei, et al.A survey on sentiment polarity classification of online reviews. Information Science, 2012, 30(8): 1263-1271.]
[24]	乐国安, 董颖红, 陈浩, 等. 在线文本情感分析技术及应用. 心理科学进展, 2013, 21(10): 1711-1719. doi: 10.3724/SP.J.1042.2013.01711
	[Yue Guo'an, Dong Yinghong, Chen Hao, et al. Online textual sentiment analysis technology and its applications. Advances in Psychological Science, 2013, 21(10): 1711-1719.] doi: 10.3724/SP.J.1042.2013.01711
[25]	王祖辉, 姜维, 李一军. 在线评论情感分析中固定搭配特征提取方法研究. 管理工程学报, 2014, 28(4): 180-186. doi: 10.3969/j.issn.1004-6062.2014.04.024
	[Wang Zuhui, Jiang Wei, Li Yijun.Regular collocation features extraction method in online reviews sentiment analysis. Journal of Industrial Engineering and Engineering Management, 2014, 28(4): 180-186.] doi: 10.3969/j.issn.1004-6062.2014.04.024
[26]	Pang B, Lee L.Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales. Conference Proceedings of the ACL, 2005: 115-124. doi: 10.3115/1219840.1219855
[27]	Ye Q, Zhang Z, Law R.Sentiment classification of online reviews to travel destinations by supervised machine learning approaches. Expert Systems with Applications, 2009, 36(3): 6527-6535. doi: 10.1016/j.eswa.2008.07.035
[28]	林江豪, 阳爱民, 周咏梅, 等. 一种基于朴素贝叶斯的微博情感分类. 计算机工程与科学, 2012, 34(9): 160-165.
	[Lin Jianghao, Yang Aimin, Zhou Yongmei, et al.Classification of microblog sentiment based on naïve Bayesian. Computer Engineering & Science, 2012, 34(9): 160-165.]
[29]	杨鼎, 阳爱民. 一种基于情感词典和朴素贝叶斯的中文文本情感分类方法. 计算机应用研究, 2010, 27(10): 3737-3739. doi: 10.3969/j.issn.1001-3695.2010.10.035
	[Yang Ding, Yang Aimin.Classification approach of Chinese texts sentiment based on semantic lexicon and naive Bayesian. Application Research of Computers, 2010, 27(10): 3737-3739.] doi: 10.3969/j.issn.1001-3695.2010.10.035
[30]	Stone P J, Dunphy D C, Smith M S.The General Inquirer: A Computer Approach to Content Analysis. New York: The MIT Press, 1966.
[31]	Hu M, Liu B.Mining and Summarizing Customer Reviews. Seattle: ACM, 2004. doi: 10.1145/1014052.1014073
[32]	Price L L, Arnould E J, Tierney P.Going to extremes: Managing service encounters and assessing provider performance. Journal of Marketing, 1995, 59(2): 83-90. doi: 10.2307/1252075
[33]	Hosany S, Gilbert D.Measuring tourists' emotional experiences toward hedonic holiday destinations. Journal of Travel Research, 2010, 49(3): 513-526. doi: 10.1177/0047287509349267
[34]	Babin B J, Griffin M.The nature of satisfaction: An updated examination and analysis. Journal of Business Research, 1998, 41(2): 127-136. doi: 10.1016/S0148-2963(97)00001-5
[35]	Hosany S, Prayag G.Patterns of tourists' emotional responses, satisfaction, and intention to recommend. Journal of Business Research, 2013, 66(6): 730-737. doi: 10.1016/j.jbusres.2011.09.011
[36]	吴小根, 杜莹莹. 旅游目的地游客感知形象形成机理与实证: 以江苏省南通市为例. 地理研究, 2011, 30(9): 1554-1565. doi: 10.11821/yj2011090002
[50]	[Liu Yonghong.Logical semantic analysis on semantic stress in transitional complex sentences. Journal of College of Chinese Language and Culture of Jinan University, 2003, 8(1): 45-52.] doi: 10.3969/j.issn.1674-8174.2003.01.007

监测点	评论总数 (条)	2013年评论数 (条)	2014年评论数 (条)	2015年1-9月评论数 (条)	正面词汇数 (个)	负面词汇数 (个)
成都	48816	4260	22563	20921	173861	21149
黄山	13777	745	6319	6411	50678	8039
焦作	5278	455	2494	2218	19309	2758
喀纳斯	1836	288	752	702	6981	949
洛阳	13135	1070	6283	5421	48157	6385
西双版纳	7310	568	3768	2783	29702	4095
阳朔	12568	1119	5098	5811	47211	7700
张家界	18011	1134	7611	8894	79664	12597
合计	120731	9639	54888	53161	455563	63672

句式结构	情感极性
第一类转折词+正面情感词	消极
第一类转折词+奇数重否定+正面情感词	积极
第一类转折词+偶数重否定+正面情感词	消极
第一类转折词+负面情感词	积极
第一类转折词+奇数重否定+负面情感词	消极
第一类转折词+偶数重否定+负面情感词	积极
第二类转折词+正面情感词	积极
第二类转折词+奇数重否定+正面情感词	消极
第二类转折词+偶数重否定+正面情感词	积极
第二类转折词+负面情感词	消极
第二类转折词+奇数重否定+负面情感词	积极
第二类转折词+偶数重否定+负面情感词	消极
第一类转折词+……,第二类转折词+……	与只有第一类转折词时相同

规则	评论	成都	黄山	焦作	喀纳斯	洛阳	西双版纳	阳朔	张家界
评分法	正面评论	82.6	89.1	84.8	80.0	85.4	79.7	71.3	81.6
	中性评论	14.5	9.6	12.1	18.5	12.3	15.4	20.8	14.2
	负面评论	2.9	1.3	3.1	1.5	2.3	4.9	7.9	4.2
规则A	正面评论	93.9	92.3	91.7	95.2	93.9	93.8	91.1	93.8
	中性评论	4.4	5.7	6.3	3.8	4.4	4.3	6.1	4.3
	负面评论	1.7	2.0	2.0	1.0	1.7	1.9	2.8	1.9
规则B	正面评论	75.7	73.5	75.0	76.6	76.6	78.2	72.4	78.9
	中性评论	14.5	15.4	13.2	15.2	14.0	11.5	13.8	11.7
	负面评论	9.8	11.1	11.8	8.2	9.4	10.3	13.8	9.4
规则C1	正面评论	78.7	75.4	76.9	79.5	78.9	77.6	72.3	76.2
	中性评论	7.9	9.1	7.9	9.3	8.4	8.9	9.7	10.7
	负面评论	13.4	15.5	15.2	11.2	12.7	13.5	18.0	13.1
规则C2	正面评论	75.9	71.6	73.8	75.7	75.8	74.2	68.9	71.9
	中性评论	4.6	6.2	4.9	5.6	5.2	5.8	5.6	7.0
	负面评论	19.5	22.2	21.3	18.7	19.0	19.9	25.5	20.9
规则C3	正面评论	73.7	68.2	71.3	73.5	73.2	71.5	66.3	68.7
	中性评论	3.3	4.7	3.7	3.5	3.9	4.1	4.0	5.0
	负面评论	23.1	27.1	25.1	22.9	22.9	24.4	29.7	26.3

旅游目的地	监测结果满意度	评分法正面评论比例	规则A 正面评论比例	规则B 正面评论比例	规则C1 正面评论比例	规则C2 正面评论比例	规则C3 正面评论比例
成都	0.7950	0.8576	0.9389	0.7848	0.7818	0.7497	0.7243
黄山	0.8270	0.9066	0.934	0.7757	0.7548	0.7094	0.6668
焦作	0.7230	0.8877	0.9274	0.7926	0.7615	0.7281	0.6984
喀纳斯	0.6989	0.7536	0.9487	0.7507	0.7635	0.7236	0.6952
洛阳	0.8130	0.8685	0.9347	0.7805	0.7683	0.7340	0.7080
西双版纳	0.7560	0.8286	0.9378	0.8020	0.7614	0.7190	0.6838
阳朔	0.5994	0.7589	0.9066	0.7472	0.6995	0.6612	0.6307
张家界	0.7080	0.8421	0.9318	0.7993	0.7411	0.6938	0.6613
绝对方差		0.0115	0.0411	0.0055	0.0030	0.0035	0.0063

旅游目的地	评分法绝对方差	规则A 绝对方差	规则B 绝对方差	规则C1 绝对方差	规则C2 绝对方差	规则C3 绝对方差
成都	0.003397	0.030959	0.002492	0.001927	0.001196	0.001740
黄山	0.006980	0.014129	0.005629	0.002032	0.007080	0.013073
喀纳斯	0.016395	0.053762	0.014592	0.013774	0.010949	0.009868
阳朔	0.013679	0.058858	0.007633	0.005570	0.002167	0.001050
张家界	0.019668	0.065636	0.009530	0.008771	0.003914	0.002089
绝对方差之和	0.060120	0.223344	0.039876	0.032074	0.025306	0.027820