跳到主要內容

簡易檢索 / 詳目顯示

回結果列表
研究生： 柳子寧
Tzu-Ning Liu
論文名稱： 以線上評論探討智慧型手機重要屬性之研究 - BERT與Kano Model之應用
Exploring key attributes of smartphones through online reviews - an application of BERT and KANO model
指導教授： 陳炫碩
Shiuann-Shuoh Chen
口試委員:
學位類別： 碩士
Master
系所名稱： 管理學院 - 企業管理學系
Department of Business Administration
論文出版年： 2023
畢業學年度： 111
語文別： 英文
論文頁數： 58
中文關鍵詞： 情感分析 、文字探勘 、語言模型 、商品屬性
外文關鍵詞： BERT, Aspect-based Sentiment Analysis, Text Mining, Kano Model
相關次數： 點閱：5  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 電子商務的發展使得網路評論成為消費者和企業之間的重要溝通管道。本研究的目的在於利用網路評論資料來獲取消費者需求資訊，並用以改善產品開發策略。透過應用Kano模型和屬性情感分析(Aspect-Based Sentiment Analysis)，本研究利用三個案例研究來分析智慧型手機評論，進而探討不同品牌陣營、世代與價格帶之間，消費者對智慧型手機的看法。

    本研究利用自然語言處理技術，包括屬性提取和情感分析來檢視評論。提取出的屬性被嵌入，並採用K-means分群方法將其分組。這些屬性分組連同其情感和整體評級一起作為神經網絡模型的輸入，以確定情感對整體評分的影響。基於這些影響，將產品的屬性歸類到Kano Model中。

    研究結果顯示，消費者在寫評論的時候，會受到其比較基礎影響。例如，在觸屏時代的低價格帶中，客戶認為"藍牙"和"功能"是必要屬性，而這些屬性在中、高價格帶時卻轉變成performance屬性。這個結果顯示，在手機產品的初期階段，客戶非常重視藍牙和類似筆這樣的配件，因為過去的掌上型筆電(PDA)等類似產品也具備筆和藍牙功能。透過整合Kano模型和屬性情感分析，本研究為消費者需求分析領域做出了貢獻，使企業能夠根據網路評論中提取的消費者回饋做出更精確的產品決策。

    In the era of e-commerce, online product reviews have become an essential source of information for consumers and businesses alike. This study aims to leverage the abundance of online reviews to gain valuable insights into customer preferences and improve product development strategies. We apply the BERT and Kano Model to analyze online product reviews, conducting three case studies that can assist E-commerce retailers with marketing precision based on a better understanding of customer thought.
    Various approaches were applied to cell phone review data from 10 brands spanning November 2003 to December 2019. Important attributes were extracted and sentiment was classified using the BERT model. K-means clustering grouped these attributes based on reviewers' perspectives. The SHAP value and effect-based Kano Model were used for additional analysis.
    Regardless of generation, iPhone customers prioritize battery capacity and charging speed. A notable transition in the perception of the "battery" attribute was observed in the high price zone, attributed to increased availability and diversity of phone applications. Product comparisons, rather than the product itself, significantly influence customers' reviews. The importance of "price" has diminished over three generations, indicating a shift in preference towards more affordable options. iPhone buyers prioritize user experience, while Android phone buyers focus on functional aspects.
    We do not consider different customer segments, such as age or gender, which may impact customer satisfaction dimensions. Future research should analyze online reviews specific to target customer segments for valuable insights and tailored product strategies.
    Our study analyzes online product reviews across various brands, generations, and price zones. Utilizing the BERT model and integrating SHAP value into the Kano model, we provide comprehensive insights that surpass traditional approaches, enabling a clear understanding of customer preferences.

    Table of Contents Chinese Abstract ii English Abstract iii Table of Contents iv List of Figure vi List of Table vii Chapter 1 Introduction 1 Chapter 2 Literature Review 3 2.1 How review mining helps products 3 2.2 Aspect-based sentiment analysis 3 2.2.1 Product attribute extraction 4 2.2.2 Customer sentiment evaluation 5 2.3 Kano Model 6 2.3.1 Kano Analysis through surveys 7 2.3.2 Kano Analysis through online reviews 8 Chapter 3 Methodology 10 3.1 Dataset 10 3.1.1 Data Preprocessing 11 3.1.2 iPhone Data 12 3.1.3 Android Data 12 3.2 Extracting aspects from reviews and classify customers’ sentiment 13 3.2-1 Aspect term extraction based on LCF-ATEPC 14 3.2.2 Determine the sentiment of the reviews regarding each aspect based on LCF-ATEPC 14 3.3 Measuring the effects of sentiments toward aspects 15 3.3.1 Get word embedding of aspect terms based on Phrase-BERT 15 3.3.2 Cluster aspect terms based on cosine similarity 16 3.3.3 Calculate the effect of sentiments based on a neural network 16 3.4 Identifying each cluster's categories from reviewers’ perspective 18 3.4.1 Explaining the training results based on the Shapley Value 19 3.4.2 Categorize the clustering aspects based on the Kano Model 20 Chapter 4 Results 23 4.1 Case 1: iPhone attributes in different product model 23 4.1.1 Data Preprocessing 23 4.1.2 Aspect term extraction and sentiment classification 23 4.1.3 Build a neural network to calculate the effects of sentiments 24 4.1.4 Classify the aspects into the Kano model 26 4.1.5 Business insight of the case 27 4.2 Case 2: Cell phone attributes in different price zones and generation 28 4.2.1 Data Preprocessing 28 4.2.2 Aspect term extraction and sentiment classification 29 04.2.3 Build a neural network to calculate the effects of sentiments 29 4.2.4 Classify the aspects into the Kano model 31 4.2.5 Business insight of the case 32 4.3 Case 3: Cell phone attributes in iPhone and Android customers 37 4.3.1 Data Preprocessing 37 4.3.2 Build a neural network to calculate the effects of sentiments 37 4.3.3 Classify the aspects into the Kano model 38 4.3.4 Business insight of the case 38 4.4 Comparison of result with previous literature 39 Chapter 5 Discussion 42 5.1 Contributions 42 5.2 Limitations and future work 43 Reference: 45

    Al-Smadi, M., Talafha, B., Al-Ayyoub, M., & Jararweh, Y. (2019). Using long short-term memory deep neural networks for aspect-based sentiment analysis of Arabic reviews [Review]. International Journal of Machine Learning and Cybernetics, 10(8), 2163-2175. https://doi.org/10.1007/s13042-018-0799-4
    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. https://doi.org/10.1080/00207543.2019.1574989
    Chen, C.-D., & Ku, E. C. S. (2021). Diversified Online Review Websites as Accelerators for Online Impulsive Buying: The Moderating Effect of Price Dispersion. Journal of Internet Commerce, 20(1), 113-135. https://doi.org/10.1080/15332861.2020.1868227
    D'Aniello, G., Gaeta, M., & La Rocca, I. (2022). KnowMIS-ABSA: an overview and a reference model for applications of sentiment analysis and aspect-based sentiment analysis. ARTIFICIAL INTELLIGENCE REVIEW, 55(7), 5543-5574. https://doi.org/10.1007/s10462-021-10134-9
    Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. ArXiv, abs/1810.04805.
    El-Adly, M. I. (2019). Modelling the relationship between hotel perceived value, customer satisfaction, and customer loyalty [Article]. Journal of Retailing and Consumer Services, 50, 322-332. https://doi.org/10.1016/j.jretconser.2018.07.007
    Farhadloo, M., Patterson, R. A., & Rolland, E. (2016). Modeling customer satisfaction from unstructured data using a Bayesian approach [Article]. Decision Support Systems, 90, 1-11. https://doi.org/10.1016/j.dss.2016.06.010
    Floh, A., Koller, M., & Zauner, A. (2013). Taking a deeper look at online reviews: The asymmetric effect of valence intensity on shopping behaviour. Journal of Marketing Management, 29(5-6), 646-670. https://doi.org/10.1080/0267257X.2013.776620
    Georg Lackermair , D. K., Kenan Kanmaz. (2013). Importance of Online Product Reviews from a Consumer's Perspective. Advances in Economics and Business, 1(1), 1-5. https://doi.org/10.13189/aeb.2013.010101
    He, L., Song, W., Wu, Z., Xu, Z., Zheng, M., & Ming, X. (2017). Quantification and integration of an improved Kano model into QFD based on multi-population adaptive genetic algorithm. COMPUTERS & INDUSTRIAL ENGINEERING, 114, 183-194. https://doi.org/https://doi.org/10.1016/j.cie.2017.10.009
    Jin, J., Jia, D. P., & Chen, K. J. (2022). Mining online reviews with a Kansei-integrated Kano model for innovative product design. International Journal of Production Research, 60(22), 6708-6727. https://doi.org/10.1080/00207543.2021.1949641
    Joung, J., & Kim, H. M. (2022). Explainable neural network-based approach to Kano categorisation of product features from online reviews. International Journal of Production Research, 60(23), 7053-7073. https://doi.org/10.1080/00207543.2021.2000656
    Južnik Rotar, L., & Kozar, M. (2017). The Use of the Kano Model to Enhance Customer Satisfaction. Organizacija, 50(4), 339-351. https://doi.org/doi:10.1515/orga-2017-0025
    Kang, T.-C., Hung, S.-Y., & Huang, A. H. (2020). The Adoption of Online Product Information: Cognitive and Affective Evaluations. Journal of Internet Commerce, 19(4), 373-403. https://doi.org/10.1080/15332861.2020.1816315
    Kano, N., Seraku, N., Takahashi, F., & Tsuji, S.-i. (1984). Attractive Quality and Must-Be Quality. Journal of The Japanese Society for Quality Control, 14(2), 147-156. https://doi.org/10.20684/quality.14.2_147
    Li, N. L., Jin, X., & Li, Y. P. (2020). Identification of key customer requirements based on online reviews [Review]. Journal of Intelligent & Fuzzy Systems, 39(3), 3957-3970. https://doi.org/10.3233/jifs-200057
    Lin, S.-P., Yang, C.-L., Chan, Y.-h., & Sheu, C. (2010). Refining Kano's ‘quality attributes–satisfaction’ model: A moderated regression approach. International Journal of Production Economics, 126(2), 255-263. https://doi.org/https://doi.org/10.1016/j.ijpe.2010.03.015
    Liu, P. D., Zhang, K., Dong, X., & Wang, P. (2022). A Big Data-Kano and SNA-CRP Based QFD Model: Application to Product Design Under Chinese New E-commerce Model. IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT. https://doi.org/10.1109/TEM.2022.3227094
    Lopes, É., Correa, U., & Freitas, L. (2021). Exploring BERT for Aspect Extraction in Portuguese Language. The International FLAIRS Conference Proceedings, 34(0). https://doi.org/10.32473/flairs.v34i1.128357
    Lundberg, S. M., & Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. ArXiv, abs/1705.07874.
    Madzík, P., & Kormanec, P. (2020). Developing the integrated approach of Kano model and Failure Mode and Effect Analysis. Total Quality Management & Business Excellence, 31(15-16), 1788-1810. https://doi.org/10.1080/14783363.2018.1509699
    Martí Bigorra, A., Isaksson, O., & Karlberg, M. (2019). Aspect-based Kano categorization. International Journal of Information Management, 46, 163-172. https://doi.org/https://doi.org/10.1016/j.ijinfomgt.2018.11.004
    Matzler, K., Hinterhuber, H. H., Bailom, F., & Sauerwein, E. (1996). How to delight your customers. Journal of Product & Brand Management, 5(2), 6-18. https://doi.org/10.1108/10610429610119469
    Ozyurt, B., & Akcayol, M. A. (2021). A new topic modeling based approach for aspect extraction in aspect based sentiment analysis: SS-LDA [Article]. Expert Systems with Applications, 168, 14, Article 114231. https://doi.org/10.1016/j.eswa.2020.114231
    Park, H., & Jeon, H. (2022). The Dynamics of Customer Satisfaction Dimension based on BERT, SHAP, and Kano Model. IFAC-PapersOnLine, 55(10), 2384-2389. https://doi.org/https://doi.org/10.1016/j.ifacol.2022.10.065
    Putra, R. A. S., & Priyanto. (2021). Kano Model Analysis of Android Apps Quality from End User’s Preferences. Journal of Physics: Conference Series, 1737(1), 012016. https://doi.org/10.1088/1742-6596/1737/1/012016
    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. https://doi.org/https://doi.org/10.1016/j.im.2016.06.002
    Salini, S., & Kenett, R. S. (2009). Bayesian networks of customer satisfaction survey data [Article]. Journal of Applied Statistics, 36(11), 1177-1189, Article Pii 915736562. https://doi.org/10.1080/02664760802587982
    Shi, Y. L., & Peng, Q. J. (2021). Enhanced customer requirement classification for product design using big data and improved Kano model. ADVANCED ENGINEERING INFORMATICS, 49, Article 101340. https://doi.org/10.1016/j.aei.2021.101340
    Singh, A., Jenamani, M., Thakkar, J. J., & Rana, N. P. (2022). Quantifying the effect of eWOM embedded consumer perceptions on sales: An integrated aspect-level sentiment analysis and panel data modeling approach. JOURNAL OF BUSINESS RESEARCH, 138, 52-64. https://doi.org/10.1016/j.jbusres.2021.08.060
    Ullah, A., & Tamaki, J. (2011). Analysis of Kano-Model-Based Customer Needs for Product Development. SYSTEMS ENGINEERING, 14(2), 154-172. https://doi.org/10.1002/sys.20168
    Wang, S., Thompson, L., & Iyyer, M. (2021). Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration. Empirical Methods in Natural Language Processing.
    Wang, W. a., Pan, S. J. a., Dahlmeier, D. a., & Xiao, X. (2016). Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 616-626. https://doi.org/10.18653/v1/D16-1059
    Wu, X. (1991). Optimal quantization by matrix searching. Journal of Algorithms, 12(4), 663-673. https://doi.org/https://doi.org/10.1016/0196-6774(91)90039-2
    Yang, H., & Li, K. (2023). PyABSA: A Modularized Framework for Reproducible Aspect-based Sentiment Analysis. arXiv pre-print server. https://doi.org/10.48550/arXiv.2208.01368
    Yang, H., Zeng, B. Q., Yang, J. H., Song, Y. W., & Xu, R. Y. (2021). A multi-task learning model for Chinese-oriented aspect polarity classification and aspect term extraction [Article]. Neurocomputing, 419, 344-356. https://doi.org/10.1016/j.neucom.2020.08.001
    Zhang, J., Lu, X. C., & Liu, D. A. (2021). Deriving customer preferences for hotels based on aspect-level sentiment analysis of online reviews [Article]. Electronic Commerce Research and Applications, 49, 14, Article 101094. https://doi.org/10.1016/j.elerap.2021.101094
    Zhang, Y., Lu, H. M., Jiang, C., Li, X., & Tian, X. L. (2021). Aspect-Based Sentiment Analysis of User Reviews in 5G Networks [Article]. Ieee Network, 35(4), 228-233. https://doi.org/10.1109/mnet.011.2000400
    Zhao, A. P., & Yu, Y. (2021). Knowledge-enabled BERT for aspect-based sentiment analysis. KNOWLEDGE-BASED SYSTEMS, 227, Article 107220. https://doi.org/10.1016/j.knosys.2021.107220
    Zhou, F., Ayoub, J., Xu, Q., & Yang, X. J. (2019). A Machine Learning Approach to Customer Needs Analysis for Product Ecosystems. Journal of Mechanical Design, 142, 1. https://doi.org/10.1115/1.4044435
    Zhu, F., & Zhang, X. Q. (2010). Impact of Online Consumer Reviews on Sales: The Moderating Role of Product and Consumer Characteristics. Journal of Marketing, 74(2), 133-148. https://doi.org/10.1509/jmkg.74.2.133

    QR CODE
    :::