中文摘要
隨著科技的發展，手機消費者的偏好也隨之變化快速，對於手機業者來說，如何以快速且經濟實惠的方式研究消費者偏好是很重要的。網路評論為公開資料故容易蒐集，消費者會在購物前瀏覽商品的評論，好的評論會深刻的影響消費者的購買意願。此外，評論的幫助性也是考量評論好壞的一環，當消費者認為評論有幫助時，他們會為評論點選”有幫助”，而好的評論再進行研究上是有幫助的，然而，過去的研究鮮少將此因素納入考量。本篇論文希望將評論的幫助性納入消費者偏好研究中，透過Latent Dirichlet Allocation (LDA) 從評論中取出重要的手機屬性，接著使用情感分析了解消費者對於每個屬性的滿意程度，並利用Ensemble Neural Network (ENNM) 得到之神經網路模型的權重計算每個屬性的重要度，最後依照屬性重要度的計算結果，給予手機公司相關的建議。

Abstract
With the advance of technology, customer preference toward cellphone changes rapidly. It is important for mobile company to analyze customer preference in a(n) economic and comprehensive way. Online reviews are public data, which is easy to collect, and contains rich information that provided by customers. Customers browse reviews before buying products. Moreover, customers consider review’s quality before reading the reviews. Reviews with good quality has great influence on customer intention to buy a product. Helpful vote is one of components for customers to examine review’s quality. People press “helpful” on the review as they think is helpful. Reviews with good quality are helpful for research. However, previous researches rarely consider this component. This paper analyzed customer preference with consideration of helpful votes. Proposed method consists of Latent Dirichlet Allocation (LDA), sentiment analysis and Ensemble Neural Network (ENNM). LDA is used for extracting key cellphone attributes. Customer satisfaction toward each attribute is analyzed by sentiment analysis. By executing ENNM, attributes importance can be calculated based on weights inside each neural network. Finally, this paper gives suggestion to mobile company based on the attribute importance calculation result.

[1] Yan, T., Conrad, F. G., Tourangeau, R., & Couper, M. P. (2010). Should I Stay or Should I go: The Effects of Progress Feedback, Promised Task Duration, and Length of Questionnaire on Completing Web Surveys. International Journal of Public Opinion Research, 23(2), 131-147. doi:10.1093/ijpor/edq046
[2] Galesic, M., & Bosnjak, M. (2009). Effects of Questionnaire Length on Participation and Indicators of Response Quality in a Web Survey. Public Opinion Quarterly, 73(2), 349-360. doi:10.1093/poq/nfp031
[3] Murray, P. (1999). Fundamental issues in questionnaire design. Accident and Emergency Nursing, 7(3), 148-153. doi:https://doi.org/10.1016/S0965-2302(99)80074-5
[4] Chatterjee, P. (2001). Online reviews: do consumers use them?
[5] Duan, W., Gu, B., & Whinston, A. B. (2008). Do online reviews matter? — An empirical investigation of panel data. Decision Support Systems, 45(4), 1007-1016. doi:10.1016/j.dss.2008.04.001
[6] D’Acunto, D., Tuan, A., Dalli, D., Viglia, G., & Okumus, F. (2020). Do consumers care about CSR in their online reviews? An empirical analysis. International Journal of Hospitality Management, 85, 102342. doi:10.1016/j.ijhm.2019.102342
[7] Wang, D., Xiang, Z., Law, R., & Ki, T. P. (2016). Assessing Hotel-Related Smartphone Apps Using Online Reviews. Journal of Hospitality Marketing & Management, 25(3), 291-313. doi:10.1080/19368623.2015.1012282
[8] Jia, S. S. (2020). Motivation and satisfaction of Chinese and US tourists in restaurants: A cross-cultural text mining of online reviews. Tourism Management, 78, 104071.
[9] Lucini, F. R., Tonetto, L. M., Fogliatto, F. S., & Anzanello, M. J. (2020). Text mining approach to explore dimensions of airline customer satisfaction using online customer reviews. Journal of Air Transport Management, 83, 101760.
[10] Liang, D., Dai, Z., & Wang, M. (2021). Assessing customer satisfaction of O2O takeaway based on online reviews by integrating fuzzy comprehensive evaluation with AHP and probabilistic linguistic term sets. Applied Soft Computing, 98, 106847.
[11] Zhang, L., Chu, X., & Xue, D. (2019). Identification of the to-be-improved product features based on online reviews for product redesign. International Journal of Production Research, 57(8), 2464-2479.
[12] Chatterjee, S., & Mandal, P. (2020). Traveler preferences from online reviews: Role of travel goals, class and culture. Tourism Management, 80, 104108.
[13] Wang, A., Zhang, Q., Zhao, S., Lu, X., & Peng, Z. (2020). A review-driven customer preference measurement model for product improvement: sentiment-based importance–performance analysis. Information Systems and e-Business Management, 18(1), 61-88.
[14] Hu, N., Liu, L., & Zhang, J. J. (2008). Do online reviews affect product sales? The role
51
of reviewer characteristics and temporal effects. Information Technology and management, 9(3), 201-214.
[15] Luce, R. D., & Tukey, J. W. (1964). Simultaneous conjoint measurement: A new type of fundamental measurement. Journal of Mathematical Psychology, 1(1), 1-27. doi:10.1016/0022-2496(64)90015-x
[16] Head, M., & Ziolkowski, N. (2012). Understanding student attitudes of mobile phone features: Rethinking adoption through conjoint, cluster and SEM analyses. Computers in Human Behavior, 28(6), 2331-2339. doi:10.1016/j.chb.2012.07.003
[17] Erdem, Y., Cebi, S., & Ilbahar, E. (2021). A New Approach to Analyze Perceived Design Quality of Mobile Phone Using Fuzzy Hierarchical Conjoint Analysis, Cham.
[18] 林千惠 . (2019). 消費者對智慧型手機保障方案偏好之研究 消費者對智慧型手機保障方案偏好之研究 . (碩士 ). 國立中興大學 國立中興大學 , 台中市 . Retrieved from https://hdl.handle.net/11296/29d66c
[19] Bahasuan, H. H., & Kodrat, D. S. (2021). Customer Preference of Attributes of Skema Wooden Chair Furniture. KnE Social Sciences. doi:10.18502/kss.v5i5.8799
[20] Pleger, L. E., Mertes, A., Rey, A., & Brüesch, C. (2020). Allowing users to pick and choose: A conjoint analysis of end-user preferences of public e-services. Government Information Quarterly, 37(4). doi:10.1016/j.giq.2020.101473
[21] Wainwright, D. M. (2003). More ‘con’ than ‘joint’: problems with the application of conjoint analysis to participatory healthcare decision making. Critical Public Health, 13(4), 373-380. doi:10.1080/09581590310001615899
[22] Phillips, M. (1941). Problems of questionnaire investigation. Research Quarterly. American Association for Health, Physical Education and Recreation, 12(3), 528-537.
[23] Boyle, K. J., Holmes, T. P., Teisl, M. F., & Roe, B. (2001). A Comparison of Conjoint Analysis Response Formats. American Journal of Agricultural Economics, 83(2), 441-454. doi:10.1111/0002-9092.00168
[24] Nickerson, C. A., McCLELLAND, G. H., & Petersen, D. M. (1990). Solutions to some problems in the implementation of conjoint analysis. Behavior Research Methods, Instruments, & Computers, 22(4), 360-374.
[25] Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent dirichlet allocation. J. Mach. Learn. Res., 3(null), 993–1022.
[26] Sutherland, I., & Kiatkawsin, K. (2020). Determinants of Guest Experience in Airbnb: A Topic Modeling Approach Using LDA. Sustainability, 12(8). doi:10.3390/su12083402
[27] Guo, Y., Barnes, S. J., & Jia, Q. (2017). Mining meaning from online ratings and reviews: Tourist satisfaction analysis using latent dirichlet allocation. Tourism Management, 59, 467-483. doi:10.1016/j.tourman.2016.09.009
[28] Wang, W., Feng, Y., & Dai, W. (2018). Topic analysis of online reviews for two competitive products using latent Dirichlet allocation. Electronic Commerce Research and Applications, 29, 142-156. doi:10.1016/j.elerap.2018.04.003
52
[29] Wang, Y., Wang, X., & Chang, X. (2020). Sentiment Analysis of Consumer-Generated Online Reviews of Physical Bookstores Using Hybrid LSTM-CNN and LDA Topic Model. Paper presented at the 2020 International Conference on Culture-oriented Science & Technology (ICCST).
[30] Qi, J., Zhang, Z., Jeon, S., & Zhou, Y. (2016). Mining customer requirements from online reviews: A product improvement perspective. Information & Management, 53(8), 951-963. doi:10.1016/j.im.2016.06.002
[31] Bi, J.-W., Liu, Y., & Fan, Z.-P. (2020). Crowd intelligence: Conducting asymmetric impact-performance analysis based on online reviews. IEEE Intelligent Systems, 35(2), 92-98.
[32] Bi, J.-W., Liu, Y., Fan, Z.-P., & Cambria, E. (2019). Modelling customer satisfaction from online reviews using ensemble neural network and effect-based Kano model. International Journal of Production Research, 57(22), 7068-7088. doi:10.1080/00207543.2019.1574989
[33] Bi, J.-W., Liu, Y., Fan, Z.-P., & Zhang, J. (2019). Wisdom of crowds: Conducting importance-performance analysis (IPA) through online reviews. Tourism Management, 70, 460-478. doi:10.1016/j.tourman.2018.09.010
[34] Ali, I., Aftab, S., & Ahmad, M. (2017). Sentiment Analysis of Tweets using SVM. International Journal of Computer Applications, 177(5), 25-29. doi:10.5120/ijca2017915758
[35] Manek, A. S., Shenoy, P. D., Mohan, M. C., & R, V. K. (2016). Aspect term extraction for sentiment analysis in large movie reviews using Gini Index feature selection method and SVM classifier. World Wide Web, 20(2), 135-154. doi:10.1007/s11280-015-0381-x
[36] Liu, Y., Bi, J.-W., & Fan, Z.-P. (2017). A method for multi-class sentiment classification based on an improved one-vs-one (OVO) strategy and the support vector machine (SVM) algorithm. Information Sciences, 394-395, 38-52. doi:10.1016/j.ins.2017.02.016
[37] Manning, C. D., Surdeanu, M., Bauer, J., Finkel, J. R., Bethard, S., & McClosky, D. (2014). The Stanford CoreNLP natural language processing toolkit. Paper presented at the Proceedings of 52nd annual meeting of the association for computational linguistics: system demonstrations.
[38] Mehmood, Y., & Balakrishnan, V. (2020). An enhanced lexicon-based approach for sentiment analysis: a case study on illegal immigration. Online Information Review, 44(5), 1097-1117. doi:10.1108/oir-10-2018-0295
[39] Dulău, T.-M., & Dulău, M. (2019). Cryptocurrency–Sentiment Analysis in Social Media. Acta Marisiensis. Seria Technologica, 16(2), 1-6.
[40] Williams, L., Bannister, C., Arribas-Ayllon, M., Preece, A., & Spasic, I. (2015). The role of idioms in sentiment analysis. Expert Systems with Applications, 10. doi:10.1016/j.eswa.2015.05.039
53
[41] Denny, M. J., & Spirling, A. (2018). Text Preprocessing For Unsupervised Learning: Why It Matters, When It Misleads, And What To Do About It. Political Analysis, 26(2), 168-189. doi:10.1017/pan.2017.44
[42] Celard, P., Vieira, A. S., Iglesias, E. L., & Borrajo, L. (2020). LDA filter: A Latent Dirichlet Allocation preprocess method for Weka. PLOS ONE, 15(11), e0241701. doi:10.1371/journal.pone.0241701
[43] Jabbar, A., Iqbal, S., Tamimy, M. I., Hussain, S., & Akhunzada, A. (2020). Empirical evaluation and study of text stemming algorithms. Artificial Intelligence Review, 53(8), 5559-5588.
[44] Hickman, L., Thapa, S., Tay, L., Cao, M., & Srinivasan, P. (2020). Text preprocessing for text mining in organizational research: Review and recommendations. Organizational Research Methods, 1094428120971683.
[45] Balakrishnan, V., & Lloyd-Yemoh, E. (2014). Stemming and lemmatization: A comparison of retrieval performances.
[46] Qi, P., Zhang, Y., Zhang, Y., Bolton, J., & Manning, C. D. (2020). Stanza: A Python natural language processing toolkit for many human languages. arXiv preprint arXiv:2003.07082.
[47] Anthony W. Ulwick(2016), Jobs to be Done: Theory to Practice., IDEA BITE PRESS, United States of America, October 2016