單一客戶對旅遊服務的事後評分和文字評論有時並不必然具備一致性。由於評分如星等在認知上具較強的影響力，這樣的不一致可能對旅遊產業的潛在客戶或服務業者造成負面的影響。本研究基於不一致的評分和文字評論的情形，發現其可能對潛在客戶造成消費上的隱藏風險。同時，此不一致性亦可能無法忠實反應業者服務的狀況而具不公平性。當單一客戶之評分為正面（高分）但其文字評論則多為負面語義時，即為第一類資訊不一致。此類不一致極容易使潛在消費者在只看待評分的狀況下，造成認知落差而產生消費時之隱性風險。若單一客戶之評分為負面（低分）但其文字評論則多為正面語義時，即為第二類資訊不一致。同樣地，此類不一致則可能使服務業者在潛在消費者只看待評分的狀況下，對服務的選擇產生負面影響而產生對業者評價之不公平性。本研究透過飯店評價資料的實證分析，探討這評價的不一致性是對潛在客戶是否造成隱性風險，以及是否對服務提供者造成隱性不公平。本研究透過文字情感分析方法和統計工具以飯店評價資料為基礎進行分析，探討不同類型的旅行者如商務旅行者，夫婦，家人，朋友或單人一起旅行是否對評價不一致性所造成的隱性風險具有影響性。另外，也針對不同的飯店類型如豪華、廉價，獨立或國際連鎖，探討其是否具隱性不公平。分析結果證實，潛在客戶面臨的隱性風險要比飯店遇到隱性不公平的風險要大。這種情況主要是由於人們對服務評價的不對稱行為所致。儘管在兩個相應的定量評估中均存在相互矛盾的評論，但人們傾向給予的好評要多於對它們的貶低。關於隱性風險，潛在客戶在不同類型的酒店中可能面臨較高程度不同的隱性風險。對於隱性的不公平，無論酒店的類型如何，或者是提供評價的顧客是何種類型，隱性不公平的程度均無顯著差異。

The rating score and text sentiment of a single customer’s review does not always have consistent polarity. Since the rating or score of a service provider’s product is an important reference, the inconsistent connection between those two review components could negatively influence the potential customers, especially in the tourism industry. Based on the inconsistent rating and text review, in this study, two hypotheses are proposed. When a review tends to have higher rating score with negative text sentiment, this inconsistency might lead to the overestimation of rating and cause the hidden risk to potential customers, if they only review the rating when they select service provider. On the contrary, if a review has a lower rating score with positive text sentiment, this inconsistency seems to degrade service provider and be unfair to it. This research aims to explore the notable tendency of inconsistent rating and text review based on empirical data. The sentiment analysis method and statistical tools were utilized to examine hotel reviews as an exemplary case. Analysis of several types of customers (travel as/on/with business, couple, family, friend, or solo) was conducted to examine the internal factor affecting the hidden risk and the external one causing the hidden unfairness. Through the reverse combination, several categories of hotels (luxury vs. budget & independent vs. international chain) were considered the internal factor for the hidden injustice and external one for the covered hazard. The empirical study results reveal that the inconsistency of positive-rating and negative-sentiment is in the majority when comparing with the inconsistency of negative-rating and positive-sentiment. It also means that the potential customers face more hidden risk than the service provider encounter the hidden unfairness. This condition is mainly driven by the asymmetric behavior that emerges from people's tendency to give praising numerical ratings than the disrespecting ones, although contradicting comments exist in both corresponding quantitative assessments. Based on data analysis, regarding the hidden risk, potential customers could face significantly different degree of severity for different types of hotels under 95% confidence interval. For the degree of hidden unfairness, regardless the type of hotel and type of customer, the degree of perceived unfairness is not significantly different.

7.1. string — Common string operations (2020) Python 2.7.18 documentation. Available at: https://docs.python.org/2/library/string.html (Accessed: 3 June 2020).
Ariffin, A. A. M. and Maghzi, A. (2012) ‘A preliminary study on customer expectations of hotel hospitality: Influences of personal and hotel factors’, International Journal of Hospitality Management. Elsevier Ltd, 31(1), pp. 191–198. doi: 10.1016/j.ijhm.2011.04.012.
Baek, H., Ahn, J. and Choi, Y. (2012) ‘Helpfulness of online consumer reviews: Readers’ objectives and review cues’, International Journal of Electronic Commerce, 17(2), pp. 99–126. doi: 10.2753/JEC1086-4415170204.
Banerjee, S. and Chua, A. Y. K. (2016) ‘In search of patterns among travellers’ hotel ratings in TripAdvisor’, Tourism Management. Elsevier Ltd, 53, pp. 125–131. doi: 10.1016/j.tourman.2015.09.020.
Banerjee, S. and Chua, A. Y. K. (2019) ‘Trust in online hotel reviews across review polarity and hotel category’, Computers in Human Behavior. Elsevier, 90(December 2017), pp. 265–275. doi: 10.1016/j.chb.2018.09.010.
Bhatnagar, U. (2018) ‘Analyzing the Effect of Tripadvisor on Reservation Intention of Hotels for Travellers from New Delhi , India การว ิ เคราะห ์ ผลกระทบต ่ อการต ั ดส ิ นใจในการจองโรงแรมของน ั กท ่ องเท ี่ ยวจากน ิ วเดล ี’, 12(April), pp. 30–49.
Bickart, B. and Schindler, R. M. (2001) ‘Internet forums as influential sources of consumer information’, Journal of Interactive Marketing. Elsevier, 15(3), pp. 31–40. doi: 10.1002/dir.1014.
Brownlee, J. (2018) ‘Statistical Methods for Machine Learning: Discover how to Transform Data into Knowledge with Python’, in Machine Learning Mastery, p. 49. Available at: https://books.google.com.tw/books?id=386nDwAAQBAJ&pg=PA49&lpg=PA49&dq=selection+%3D+choice(sequence)+python&source=bl&ots=yQhiP4CPyc&sig=ACfU3U227yiAFHF4K-NyDtjSQnUzk08iPQ&hl=en&sa=X&ved=2ahUKEwj6sZKVoIDqAhUCGqYKHegaBcEQ6AEwDXoECAkQAQ#v=onepage&q=selectio (Accessed: 14 June 2020).
Chang, W. and Wang, J. (2018) ‘Electronic Commerce Research and Applications Mine is yours ? Using sentiment analysis to explore the degree of risk in the sharing economy’, Electronic Commerce Research and Applications. Elsevier B.V., 28, pp. 141–158. doi: 10.1016/j.elerap.2018.01.014.
Chen, J. S. and Hsu, C. H. C. (2000) ‘Measurement of Korean tourists’ perceived images of overseas destinations’, Journal of Travel Research. doi: 10.1177/004728750003800410.
Constantinides, E. and Fountain, S. J. (2008) ‘Web 2.0: Conceptual foundations and marketing issues’, Journal of Direct, Data and Digital Marketing Practice, 9(3), pp. 231–244. doi: 10.1057/palgrave.dddmp.4350098.
Constantinides, E. and Holleschovsky, N. I. (2016) ‘Impact of online product reviews on purchasing decisions’, WEBIST 2016 - Proceedings of the 12th International Conference on Web Information Systems and Technologies, 1(January 2016), pp. 271–278. doi: 10.5220/0005861002710278.
Dahl, S. (2018) Social Media Marketing: Theories and Applications. Second Edi. Edited by M. Waters. UK: Sage. Available at: https://books.google.com.tw/books?id=iPlNDwAAQBAJ&pg=PA187&lpg=PA187&dq=online+reviews+are+more+credible+than+marketing&source=bl&ots=plC1NRp8E6&sig=ACfU3U14AUPlBYHiIGdNbiMQ_EIjpdsnKQ&hl=en&sa=X&ved=2ahUKEwizoovmu8rpAhV8KqYKHbZtD6cQ6AEwD3oECAoQAQ#v=onepag (Accessed: 24 May 2020).
Deho, O. B. et al. (2018) ‘Sentiment analysis with word embedding’, IEEE International Conference on Adaptive Science and Technology, ICAST. IEEE, 2018-Augus(March), pp. 1–4. doi: 10.1109/ICASTECH.2018.8506717.
Floyd, M. F. et al. (2004) ‘The effect of risk perceptions on intentions to travel in the aftermath of september 11, 2001’, Journal of Travel and Tourism Marketing, 15(2–3), pp. 19–38. doi: 10.1300/J073v15n02_02.
Fu, B. et al. (2013) ‘Why people hate your App - Making sense of user feedback in a mobile app store’, Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Part F1288, pp. 1276–1284. doi: 10.1145/2487575.2488202.
Garzia, F. et al. (2018) ‘Perceived Risk Assessment through Open-Source Intelligent Techniques for Opinion Mining and Sentiment Analysis: The Case Study of the Papal Basilica and Sacred Convent of Saint Francis in Assisi, Italy’, Proceedings - International Carnahan Conference on Security Technology. IEEE, 2018-Octob, pp. 1–5. doi: 10.1109/CCST.2018.8585519.
Geierhos, M. et al. (2015) ‘“I grade what i get but write what i think.” inconsistency analysis in patients’ reviews’, 23rd European Conference on Information Systems, ECIS 2015, pp. 0–15.
Han, J., Micheline, K. and Pei, J. (2012) Data Mining: Concepts and Techniques. Amsterdam: Elsevier. Available at: https://www.google.com/books/edition/Data_Mining_Concepts_and_Techniques/pQws07tdpjoC?hl=en&gbpv=1&pg=PA111 (Accessed: 19 May 2020).
Hennig-Thurau, T. et al. (2004) ‘Electronic word-of-mouth via consumer-opinion platforms: What motivates consumers to articulate themselves on the Internet?’, Journal of Interactive Marketing, 18(1), pp. 38–52. doi: 10.1002/dir.10073.
Hu, N., Koh, N. S. and Reddy, S. K. (2014) ‘Ratings lead you to the product, reviews help you clinch it? the mediating role of online review sentiments on product sales’, Decision Support Systems, pp. 42–53. doi: 10.1016/j.dss.2013.07.009.
Huang, L. S. (2015) ‘Trust in product review blogs: The influence of self-disclosure and popularity’, Behaviour and Information Technology, 34(1), pp. 33–44. doi: 10.1080/0144929X.2014.978378.
Hubert, M., Rousseeuw, P. and Verdonck, T. (2009) ‘Robust PCA for skewed data and its outlier map’, Computational Statistics and Data Analysis. Elsevier B.V., 53(6), pp. 2264–2274. doi: 10.1016/j.csda.2008.05.027.
Hubert, M. and Van Der Veeken, S. (2008) ‘Outlier detection for skewed data’, Journal of Chemometrics, 22(3–4), pp. 235–246. doi: 10.1002/cem.1123.
Hutto, C. J. and Gilbert, E. E. (2014) ‘VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text. Eighth International Conference on Weblogs and Social Media (ICWSM-14).”’, Proceedings of the 8th International Conference on Weblogs and Social Media, ICWSM 2014. Available at: http://sentic.net/.
Islam, M. R. (2014) ‘Numeric rating of Apps on Google Play Store by sentiment analysis on user reviews’, 1st International Conference on Electrical Engineering and Information and Communication Technology, ICEEICT 2014, (June). doi: 10.1109/ICEEICT.2014.6919058.
Ito, T. A. et al. (1998) ‘Negative information weighs more heavily on the brain: The negativity bias in evaluative categorizations.’, Journal of Personality and Social Psychology. doi: 10.1037//0022-3514.75.4.887.
Jang, W., Kim, J. and Park, Y. (2014) ‘Why the online customer reviews are inconsistent? Textual review vs. scoring review’, in Advances in Intelligent Systems and Computing, pp. 151–151. doi: 10.1007/978-3-319-04313-5_20.
Jolliffe, I. T. (2002) Principal components analysis. Second Edi, Springer. Second Edi. New York: Springer. doi: 10.1016/B978-0-08-044894-7.01358-0.
Kahneman, D. et al. (1979) ‘Prospect Theory : An Analysis of Decision under Risk’, Econometrica, 47(2), pp. 263–292. Available at: http://www.jstor.org/stable/1914185%5Cnhttp://www.jstor.org/%5Cnhttp://www.jstor.org/action/showPublisher?publisherCode=econosoc.%5Cnhttp://www.jstor.org.
Keates, N. (2007) Deconstructing TripAdvisor, The Wall Street Journal. Available at: https://www.wsj.com/articles/SB118065569116920710 (Accessed: 14 June 2020).
Kiat, A. L. W. (2019) The English Language Multilingual Processing for Sentiment Analysis in Social Media by Using Python NLTK Text Classification, Miopia, and MeaningCloud Sentiment Analysis Techniques. Universiti Malaysia Pahang.
Koh, N. S. (2011) ‘The Valuation of User-Generated Content: A Structural, Stylistic and Semantic Analysis of Online Reviews’, Dissertations and Theses Collection (Open Access), pp. 1–168. Available at: https://libproxy.library.unt.edu/login?url=http://search.proquest.com/docview/1018690548?accountid=7113.
Kontopoulos, E. et al. (2013) ‘Ontology-based sentiment analysis of twitter posts’, Expert Systems with Applications, 40(10), pp. 4065–4074. doi: 10.1016/j.eswa.2013.01.001.
Kusumasondjaja, S., Shanka, T. and Marchegiani, C. (2012) ‘Credibility of online reviews and initial trust: The roles of reviewer’s identity and review valence’, Journal of Vacation Marketing, 18(3), pp. 185–195. doi: 10.1177/1356766712449365.
Lo, A. S., Cheung, C. and Law, R. (2011) ‘Hong kong residents’ adoption of risk reduction strategies in leisure travel’, Journal of Travel and Tourism Marketing. doi: 10.1080/10548408.2011.562851.
Loria, S. (2020) TextBlob Documentation. Available at: https://textblob.readthedocs.io/en/dev/.
Manning, C. et al. (2015) ‘The Stanford CoreNLP Natural Language Processing Toolkit’, (March), pp. 55–60. doi: 10.3115/v1/p14-5010.
MeaningCloud (2020) What is Sentiment Analysis? Available at: https://www.meaningcloud.com/developer/sentiment-analysis/doc/2.1 (Accessed: 3 June 2020).
Murphy, R. (2018) Local Services Ads Click Study: Where Do People Click on Local SERPs?, BrightLocal. Available at: https://www.brightlocal.com/research/local-services-ads-click-study/ (Accessed: 26 February 2020).
Nelson, P. (1970) ‘Information and Consumer Behavior’, Journal of Political Economy, 78(2), pp. 311–329. doi: 10.1086/259630.
Nielsen, F. Å. (2011) ‘A new ANEW: Evaluation of a word list for sentiment analysis in microblogs’, CEUR Workshop Proceedings, 718, pp. 93–98.
O’Connor, P. (2010) ‘Managing a hotel’s image on Tripadvisor’, Journal of Hospitality Marketing and Management, 19(7), pp. 754–772. doi: 10.1080/19368623.2010.508007.
Öǧüt, H. and Onur Taş, B. K. (2012) ‘The influence of internet customer reviews on the online sales and prices in hotel industry’, Service Industries Journal. doi: 10.1080/02642069.2010.529436.
Park, D. H. and Lee, J. (2008) ‘eWOM overload and its effect on consumer behavioral intention depending on consumer involvement’, Electronic Commerce Research and Applications. doi: 10.1016/j.elerap.2007.11.004.
Rico-Juan, J. R., Gallego, A. J. and Calvo-Zaragoza, J. (2019) ‘Automatic detection of inconsistencies between numerical scores and textual feedback in peer-assessment processes with machine learning’, Computers and Education. Elsevier, 140(February), p. 103609. doi: 10.1016/j.compedu.2019.103609.
Ritchie, B. W. and Jiang, Y. (2019) ‘A review of research on tourism risk, crisis and disaster management: Launching the annals of tourism research curated collection on tourism risk, crisis and disaster management’, Annals of Tourism Research. Elsevier, 79(September), p. 102812. doi: 10.1016/j.annals.2019.102812.
robpca function (2020) R Documentation. Available at: https://www.rdocumentation.org/packages/rospca/versions/1.0.4/topics/robpca (Accessed: 19 June 2020).
Roehl, W. S. and Fesenmaier, D. R. (1992) ‘Risk Perceptions and Pleasure Travel: An Exploratory Analysis’, Journal of Travel Research. doi: 10.1177/004728759203000403.
Rozin, P. and Royzman, E. B. (2001) ‘Negativity bias, negativity dominance, and contagion’, Personality and Social Psychology Review, 5(4), pp. 296–320. doi: 10.1207/S15327957PSPR0504_2.
Schuckert, M., Liu, X. and Law, R. (2015) ‘Hospitality and Tourism Online Reviews: Recent Trends and Future Directions’, Journal of Travel and Tourism Marketing, 32(5), pp. 608–621. doi: 10.1080/10548408.2014.933154.
Schuckert, M., Liu, X. and Law, R. (2016) ‘Insights into Suspicious Online Ratings: Direct Evidence from TripAdvisor’, Asia Pacific Journal of Tourism Research, 21(3), pp. 259–272. doi: 10.1080/10941665.2015.1029954.
seaborn.pointplot (2020) seaborn 0.10.1 documentation.
Shan, G. et al. (2018) ‘Inconsistency investigation between online review content and ratings’, Americas Conference on Information Systems 2018: Digital Disruption, AMCIS 2018, pp. 2–11.
Shi, X. and Liang, X. (2015) ‘Resolving inconsistent ratings and reviews on commercial webs based on support vector machines’, 2015 12th International Conference on Service Systems and Service Management, ICSSSM 2015. doi: 10.1109/ICSSSM.2015.7170152.
Shrestha, N. and Nasoz, F. (2019) ‘Deep Learning Sentiment Analysis of Amazon.Com Reviews and Ratings’, International Journal on Soft Computing, Artificial Intelligence and Applications, 8(1), pp. 01–15. doi: 10.5121/ijscai.2019.8101.
Singh, A., Ramasubramanian, K. and Shivam, S. (2019) Building an Enterprise Chatbot, Building an Enterprise Chatbot. doi: 10.1007/978-1-4842-5034-1.
Sirakaya, E. and Woodside, A. G. (2005) ‘Building and testing theories of decision making by travellers’, Tourism Management, 26(6), pp. 815–832. doi: 10.1016/j.tourman.2004.05.004.
Sönmez, S. F. and Graefe, A. R. (1998) ‘Influence of terrorism risk on foreign tourism decisions’, Annals of Tourism Research. doi: 10.1016/s0160-7383(97)00072-8.
statsmodels.graphics.gofplots.qqplot (2020) statsmodels v0.11.1. Available at: https://www.statsmodels.org/stable/generated/statsmodels.graphics.gofplots.qqplot.html (Accessed: 19 June 2020).
Sthapit, E. and Björk, P. (2019) ‘Sources of distrust: Airbnb guests’ perspectives’, Tourism Management Perspectives, 31(May), pp. 245–253. doi: 10.1016/j.tmp.2019.05.009.
string — Common string operations (2020) Python 3.8.3 documentation. Available at: https://docs.python.org/3/library/string.html (Accessed: 3 June 2020).
Tsang, A. S. L. and Prendergast, G. (2009) ‘Is a “star” worth a thousand words?: The interplay between product-review texts and rating valences’, European Journal of Marketing, 43(11), pp. 1269–1280. doi: 10.1108/03090560910989876.
Uppink Calderwood, L. and Soshkin, M. (2019) The Travel & Tourism Competitiveness Report 2019 Travel and Tourism at a Tipping Point. Geneva.
Valdivia, A. et al. (2019) ‘Inconsistencies on TripAdvisor reviews: A unified index between users and Sentiment Analysis Methods’, Neurocomputing. Elsevier B.V., 353, pp. 3–16. doi: 10.1016/j.neucom.2018.09.096.
Valdivia, A., Luzón, M. V. and Herrera, F. (2017) ‘Sentiment Analysis in TripAdvisor’, IEEE Intelligent Systems, 32(4), pp. 72–77. doi: 10.1109/mis.2017.3121555.
Wang, L. et al. (2014) ‘Consumer trust in tourism and hospitality: A review of the literature’, Journal of Hospitality and Tourism Management. Elsevier Ltd, 21, pp. 1–9. doi: 10.1016/j.jhtm.2014.01.001.
Wang, W., Song, Y. and Chen, B. (2015) ‘A Correction Method of Online Product Scores from the Perspective of Discourse Markers Theory’, Proceedings of the 3rd International 7 Conference on Material, Mechanical and Manufacturing Engineering, 1(ic3me), pp. 1195–1200. doi: 10.2991/ic3me-15.2015.231.
Waskom, M. (2020) seaborn.heatmap, seaborn 0.10.1 documentation. Available at: https://seaborn.pydata.org/generated/seaborn.heatmap.html (Accessed: 20 May 2020).
Williams, A. M. and Baláž, V. (2015) ‘Tourism Risk and Uncertainty: Theoretical Reflections’, Journal of Travel Research, 54(3), pp. 271–287. doi: 10.1177/0047287514523334.
Xanthopoulos, P., Pardalos, P. M. and Trafalis, T. B. (2012) Robust Data Minig. doi: 10.1007/978-1-4419-9878-1.
Yang, B. (2013) ‘The Effect Of Online Customer Reviews On Customer ’ s Perceived Risk Associated With Online Leisure Hotel Booking’, The Effect Of Online Customer Reviews On Customer ’ s Perceived Risk Associated With Online Leisure Hotel Booking.
Ye, Q. et al. (2011) ‘The influence of user-generated content on traveler behavior: An empirical investigation on the effects of e-word-of-mouth to hotel online bookings’, Computers in Human Behavior. Elsevier Ltd, 27(2), pp. 634–639. doi: 10.1016/j.chb.2010.04.014.
Yeung, T. A. and Law, R. (2004) ‘Extending the modified heuristic usability evaluation technique to chain and independent hotel websites’, International Journal of Hospitality Management. doi: 10.1016/j.ijhm.2003.03.001.
Yi, J., Yuan, G. and Yoo, C. (2020) ‘The effect of the perceived risk on the adoption of the sharing economy in the tourism industry: The case of Airbnb’, Information Processing and Management. Elsevier, 57(1), p. 102108. doi: 10.1016/j.ipm.2019.102108.
Zhou, S. and Guo, B. (2015) ‘The interactive effect of review rating and text sentiment on review helpfulness’, in Lecture Notes in Business Information Processing. doi: 10.1007/978-3-319-27729-5_8.