簡易檢索 / 詳目顯示

回結果列表
研究生： Faturochman Pranacahya Andrianto
Faturochman Pranacahya Andrianto
論文名稱： 基於屬性情感分類及貝氏方法的消費者偏好分析與拆解
Consumer Preference Analysis and Disaggregation Based on Aspect-Level Sentiment Classification and Bayesian Approach
指導教授： 林希偉
Shi-Woei Lin
口試委員: 彭奕農
陳志萍
學位類別： 碩士
Master
系所名稱： 管理學院 - 工業管理系
Department of Industrial Management
論文出版年： 2023
畢業學年度： 112
語文別： 英文
論文頁數： 52
中文關鍵詞： 屬性類別檢測 、自然語言處理 、文本資料探勘 、屬性情感分析 、多準則決策 、貝氏線性回歸
外文關鍵詞： Aspect category detection, natural language processing, text mining, aspect-level sentiment analysis, multi-attribute decision making, Bayesian linear model
相關次數： 點閱：22  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

    • 網路上的評論是累積產品回饋的可靠來源，有助於確定消費者對產品的偏好的程度，在網路平臺上，消費者不僅有機會表達他們對產品的整體評價（如星等），也可以透過文字敘述表達他們的細部觀點。本研究旨在創建一個基於屬性情感分析的框架，評估消費者對於產品（或服務）不同面向之品質的觀點，並進一步透過多屬性決策分析之分解模型，掌握消費者在產品不同面向的偏好。本研究在使用Hugging Face社群中，基於先進的 transformer 模型的預訓練模型提取消費者評論中的產品屬性，並將每個被提取出來屬性進行情感分類，然後透過再潛在狄利克雷分配方法歸類這些屬性，以取得每個評論在不同的評分面向（即產品或服務之品質面向）上的得分，最後再依據消費者給出的總體評分或星級，以多準則決策模型的偏好拆解的方式結合貝氏線性模型求得消費者針對不同面向的重視程度（即權重）。本研究所提出之分析框架可掌握消費者在評比整個產品時最看重的面向，研究結果可以協助管理人員更精準地瞭解產品中需要改進和強化的方面。

    Reviews and critiques on the internet serve as reliable sources for accumulating product feedback, adding to determining the extent of consumer preferences towards a product. On some platforms, consumers not only have the opportunity to express their overall evaluations of products (such as star ratings) but can also convey their detailed perspectives through textual descriptions. This research aims to construct a framework based on aspect-level sentiment analysis to assess consumers’ viewpoints on different facets of product (or service) quality. Furthermore, through a preference disaggregation model of multi-attribute decision analysis, it seeks to understand consumer preferences across various product dimensions. In particular, an advanced transformer model, a pre-trained model available within the Hugging Face community, were utilized to extract product aspects from consumer reviews. Each extracted aspect undergoes sentiment classification, and a Latent Dirichlet allocation (LDA) method is then employed for aspect categorization. This process yields scores across different rating dimensions for each review. Subsequently, using a preference disaggregation approach through a Bayesian linear model within a multi-attribute decision analysis framework, this study derives the importance weights assigned to different dimensions by consumers (when evaluating a product or a service). The analytical framework proposed in this study allows for the identification of the aspects that consumers prioritize when evaluating a product. The research findings can assist managers in gaining a more precise understanding of the dimension within a product that requires improvement and reinforcement.

    ACKNOWLEDGEMENT i ABSTRACT ii 中文摘要 iii TABLE OF CONTENTS iv LIST OF FIGURES vi LIST OF TABLES vii Chapter 1 Introduction 1 1.1 Background 1 1.2 Problem Definition 2 1.3 Purpose of the Research 4 1.4 Organization of Thesis 4 Chapter 2 Literature Review 5 2.1 Aspect-Level Sentiment Analysis 5 2.2 Aspect Category Detection 8 2.3 Multi-Criteria Decision Analysis 11 Chapter 3 Methods and Materials 13 3.1 Proposed Framework 13 3.2 Data Acquisition and Preparation 15 3.3 Aspect Level Sentiment Analysis 17 3.3.1 Task Definition 20 3.3.2 Semantic-Relative Distance 20 3.3.3 Embedding Layer 21 3.3.4 Pre-Feature Extractor 21 3.3.5 Feature Extractor 22 3.3.6 Feature Interactive Learning Layer 22 3.3.7 Output Layer 23 3.3.8 Model Training 23 3.4 Aspect Category Detection 23 3.5 Preference Disaggregation Analysis in Multi-Criteria Decision Analysis 25 3.6 Bayesian Linear Model 26 Chapter 4 Results 28 4.1. Data Collection and Preprocessing 28 4.2. Aspect-Level Sentiment Analysis 32 4.3. Aspect Categorization 34 4.4. Preference Disaggregation 40 4.5. Final Discussion 44 Chapter 5 Conclusion 47 5.1. Summary 47 5.2. Limitations and Future Works 48 5.3. Contributions 49 REFERENCES 50

    Abalo, J., Varela, J. & Manzano, V., 2007. Importance values for Importance–Performance Analysis: A formula for spreading out values derived from preference rankings. Journa of Business Research, 60(2), pp. 115-121.
    Akhtar, M. S., Ekbal, A. & Bhattacharyya, P., 2016. Aspect based sentiment analysis: category detection and sentiment classification for Hindi. Proceedings of the 17th International Conference on Computational Linguistics and Intelligent Text Processing, pp. 246-257.
    Al-Ghurubi, S. M., Noah, S. A. M. & Tiun, S., 2020. Unsupervised Semantic Approach of aspect-based sentiment analysis for large-scale user reviews. IEEE Access Vol. 8, pp. 218592 - 218613.
    Andono, P. N., Sunardi, Nugroho, R. A. & Harjo, B., 2022. Aspect-Based Sentiment Analysis for Hotel Review Using LDA, Semantic Similarity, and BERT. International Journal of Intelligent Engineering and Systems, Vol.15, No.5, 2022, pp. 232-243.
    Blei, D. M., Ng, A. Y. & Jordan, M. I., 2003. Latent Dirichlet Allocation. Journal of Machine Learning Research , Volume 3, pp. 993-1022.
    Brauwers, G. & Frasincar, F., 2022. A Survey on Aspect-Based Sentiment Classification. ACM comput. Surv. 55 4 Article 65, pp. 1-37.
    Cao, J., Li, J., Yin, M. & Wang, Y., 2023. Online Reviews Sentiment Analysis and Product Feature. ACM Trans. Asian Low-Resour. Lang. Inf. Process. 22, pp. 1-17.
    Chebolu, S. U. S., Rosso, P., Kar, S. & Solorio, T., 2022. Survey on Aspect Category Detection. ACM Computer Survey Vol. 55 Issue 7 No. 132, pp. 1-37.
    Devi, D. V. N., Kumar, C. K. & Prasad, S., 2016. A feature based approach for sentiment analysis by using support vector machine. Proceedings of the 6th International Conference on Advanced Computing, pp. 3-8.
    Duompos, M., Grigoroudis, E., Matsatsinis, N. F. & Zopounidis, C., 2022. Preference Disaggregation Analysis: An Overview of Methodological Advances and Applications. Intelligent Decision Support Systems, pp. 73-100.
    Edwards, W., 1977. How to Use Multiattribute Utility Measurement for Social Decisionmaking. IEEE Transactions on System, Man, Cybernetics, Vol. SMC-7, NO. 5, pp. 326-340.
    Edwards, W. & Barron, F. H., 1994. SMARTS and SMARTER: Improved Simple Methods for Multiattribute Utility Measurement. Organizational Behaviour and Human Decision Process 60, pp. 306-325.
    Ehsanifar, M., Wood, D. A. & Babaie, A., 2020. UTASTAR method and its application in multi-criteria warehouse. Operations Management Research, pp. 202-215.
    Fang, J. & Partovi, F. Y., 2021. Criteria determination of analytic hierarchy process using a topic model. Expert Systems With Applications, Volume 169, pp. 1-13.
    Fransiska, S., Rianto & Gufroni, A. I., 2020. Sentiment Analysis Provider by.U on Google Play. Scientific Journal of Informatics Vol. 7 No. 2, pp. 203-212.
    Griffiths, T. L. & Steyvers, M., 2004. Finding Scientific topics. Proceedings of the National academy of Sciences, pp. 5228-5235.
    Guidotti, R. et al., 2018. A Survey of Methods for Explaining Black Box Models. Computing Surveys 51, pp. 1-42.
    Guo, M., Liao, X., Liu, J. & Zhang, Q., 2020. Consumer preference analysis: A data-driven multiple criteria approach integrating online information. Omega Vol. 96, pp. 1-16.
    Hercig, T., Brychcín, T., Svoboda, L. & Konkol, M., 2016. UWB at SemEval-2016 Task 5: Aspect Based Sentiment Analysi. Proceedings of SemEval-2016, pp. 342-349.
    Hu, M. & Liu, B., 2004. Mining and Summarizing Customer Reviews. Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 168-177.
    Hu, M. & Liu, B., 2006. Opinion Extraction and Summarization on the Web. National conference on Artificial intelligence - Volume 2 , pp. 1621-1624.
    Keeney, R. L. & Raiffa, H., 1976. Decisions with Multiple Objectives. Cambridge: Cambridge University Press .
    Khotimah, D. A. K. & Sarno, R., 2019. Sentiment Analysis of Hotel Aspect Using Probabilistic Latent Semantic Analysis,. International Journal of Intelligent Engineering and Systems, Vol.12, No.4, pp. 275 - 290.
    Kiritchenko, S., Zhu, X., Cherry, C. & Mohammad, S., 2014. Detecting aspects and sentiment in customer reviews. Proceedings of the 8th International Workshop on Semantic Evaluation, pp. 437-442.
    Kumar, A., Saini, M. & Sharan, A., 2020. Aspect category detection using statistical and semantic association. Computation Intelligence, pp. 1161-1182.
    Lagreze, E. J. & Siskos, J., 1982. Assessing a set of additive utility functions for multicriteria decision-making, the UTA method. European Journal of Operational Research Vol. 10 Issue 2, pp. 151-164.
    Lakiotaki, K., Tsafarakis, S. & Matsatsinis, N., 2008. UTA-Rec: A Recommender System based on Multiple Criteria Analysis. ACM conference on Recommender System, pp. 219-226.
    Liu, B., 2012. Sentiment Analysis and Opinion Mining. s.l.:Morgan & Claypool.
    Li, X. et al., 2020. Enhancing BERT representation with context-aware embedding for aspect-based sentiment analysis. IEEE Access , Volume 8, pp. 46868-46876.
    Lolli, F. et al., 2019. On the elicitation of criteria weights in PROMETHEE-based ranking. Expert Systems With Application, pp. 217-227.
    Ray, P. & Chakrabarti, A., 2019. A mixed approach of deep learning method and rule-based method to improve aspect level sentiment analysis. Elsevier, pp. 1-9.
    Saaty, T. L. & Vargas, L., 2006. The Analytic Network Process. pp. 1-26.
    Schouten, K. & Frasincar, F., 2015. Survey on aspect-level sentiment analysis. IEEE Transactions on Knowledge 28 Vol.3, pp. 813-830.
    Schouten, K., Frasincar, F. & Jong, F. d., 2014. COMMIT-P1WP3: A Co-occurrence Based Approach to Aspect-Level Sentiment Analysis. Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pp. 203-207.
    Siskos, Y., Grigoroudis, E. & Matsatsinis, N. F., 2005. UTA Methods. In: Multiple Criteria Decision Analysis State of the Art Surveys. Boston: Springer Science + Business Media, Inc., pp. 297-343.
    Songpan, W., 2017. The Analysis and Prediction of Customer Review. 2017 IEEE 15th International Conference on Software Engineering Research, Management and Applications (SERA), pp. 71-77.
    Song, Y., Li, G., Li, T. & Li, Y., 2021. A purchase decision support model considering consumer personalization. Journal of Retailing and Consumer Services, pp. 1-11.
    Suadaa, L. H. & Purwarianti, A., 2016. Combination of Latent Dirichlet Allocation (LDA) and Term. Fourth International Conference on Information and Communication Technologies, pp. 1-6.
    Sun, C., Huang, L. & Qiu, X., 2019. Utilizing bert for aspect-based sentiment analysis via constructing auxiliary sentence.
    Tang, D., Qin, B., Feng, X. & Liu, T., 2016. Effective LSTMs for Target-Dependent Sentiment Classification. Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pp. 3298-3307.
    Wang, H., Yue, L. & Zhai, C., 2010. Latent Aspect Rating Analysis on Review Text Data: A Rating Regression Approach. Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.
    Yang, H. & Li, K., 2022. PyABSA: Open Framework for Aspect-based Sentiment Analysis.
    Yang, H., Zhang, C. & Li, K., 2023. Pyabsa: A modularized framework for reproducible aspect-based sentiment analysis. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, pp. 5117-5122.
    Yenkikar, A., Babu, N. & Sangve, S., 2019. R-SA: A Rule-based Expert System for Sentiment. IEEE Pune Section International Conference (PuneCon), pp. 1-7.
    You, L. et al., 2022. ASK-RoBERTa: A pretraining model for aspect-based sentiment classification via sentiment knowledge mining. Knowledge-Based Systems 253.
    Yu, J., Zha, Z.-J., Wang, M. & Chua, T.-S., 2011. Aspect ranking: Identifying important product aspect from online consumer reviews. n Proceedings of the 49th Annual Meeting of the Association for Computational Linguistic , pp. 1496-1505.
    Zeng, B. et al., 2019. LCF: A Local Context Focus Mechanism for Aspect-Based Sentiment Classification. Applied Science, Volume 9, pp. 1-22.
    Zhang, Z. & Nie, J.-Y., 2015. TJUdeM: A Combination Classifier for Aspect Category Detection. Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), p. s 772–777.
    Zhuang, L., Jing, F. & Zhu, X.-Y., 2006. Movie Review Mining and Summarization. Proceedings of the 15th ACM International Conference on Information and Knowledge Management, pp. 43-50.
    Zhu, J., Wang, H., Tsou, B. K. & Zhu, M., 2009. Multi-aspect opinion polling from textual reviews. Proceedings of the 18th ACM Conference on Information and Knowledge Management, pp. 1799-1802.

    無法下載圖示 全文公開日期 2027/02/05 (校內網路)
    全文公開日期 2034/02/05 (校外網路)
    全文公開日期 2034/02/05 (國家圖書館：臺灣博碩士論文系統)
    QR CODE