簡易檢索 / 詳目顯示

回結果列表
研究生： 趙雅蘭
Chao, Ya-Lan
論文名稱： 應用深度學習於教學討論平台之短語分類方法
Short Text Classification on Education Discussion Platform via Deep Learning
指導教授： 王惠嘉
Wang, Hei-Chia
學位類別： 碩士
Master
系所名稱： 管理學院 - 資訊管理研究所
Institute of Information Management
論文出版年： 2019
畢業學年度： 107
語文別： 英文
論文頁數： 74
中文關鍵詞： 文字分群 、文字分類 、卷積神經網路 、主題偵測模型
外文關鍵詞： Text Clustering, Text Classification, Convolutional Neural Network (CNN), Topic Modeling
相關次數： 點閱：126  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

    • 近十年來隨著網際網路的發展，數位學習也隨之日新月異。從提供學習者唯讀功能的數位學習1.0到讀寫功能兼具的數位學習2.0，再從讀寫功能兼具的數位學習2.0發展至客製化學習者學習環境的數位學習3.0。
    然而，即便是數位學習3.0，此科技技術仍單方面地著重於提升學習者的使用體驗，而忽略了對教學者可能造成的衝擊。事實上，資訊爆炸的時代之下，當今的學習者可透過多元管道獲取各種知識。當今學習者已與幾十年前的學習者有著截然不同的思維與學習方式。因此，教學者愈來愈難以掌握學生的學習觀點，許多教學者無法完全掌握當今適合的指導方針。
    本研究旨在協助教學者在數位學習的環境下更加掌握學習者的學習問題。先將網路學習者討論平台上的發表問題分為主要的學習問題面向。接者，為各個學習問題面向做主題偵測，藉此檢測每種學習問題面向內的子問題。最後，本研究總結了該領域的主要學習問題面向以及其中的子問題，使教學者更加了解學習者的學習問題，使教學者得以為學習者設計出更事宜的課程教學內容。
    整體而言，本研究旨在進一步分析線上討論平台上的問題，向教學者傳達未來課程該關注的重點內容，從而幫助當今教學者更加掌握數位學習環境席捲而來的教學問題。

    As the evolution of the Internet over the decades, e-learning has evolved throughout the years as well. From e-Learning 1.0 to e-Learning 3.0, learners experience a read-only medium to a read-write medium, and from a read-write medium to a customized learning environment. However, previous studies mainly focus on upgrading the experience of the learners, neglecting the role of instructors. In fact, as bombarded information flows into the sites, students nowadays can take in diverse knowledge through numerous channels and thus, pupils these days think and learn in the distinct mode, which is not the same as the way students did back in decades ago.
    Thus, it is getting more and more difficult for teachers to capture the pinpoints of
    students nowadays.
    This study aims to classify the questions asked on a discussion board website into several learning problem types. Moreover, by detecting the topics within each learning problem type, this study then clarifies more detail learning sub-problems within.
    Afterwards, this study summarizes the main problem types of this field and its subtopics within each problem type for instructors to gain better ideas with pupils’ learning condition and on how to design the relevant courses in the future.
    In short, this study seeks to figure out the problems of learners from the questions asked on the discussion board online and further inform the instructors what the key
    emphasis should be put in the future courses, and thus assist the teachers nowadays to have a more enjoyable and effective ride through the storm of e-Learning.

    Chapter 1. Introduction 1 1.1. Research Background and Motivation 1 1.2. Research Purposes 5 1.3. Research Scope and Limitation 10 1.4. Research Procedure 10 1.5. Research Outline 12 Chapter 2. Literature Review 13 2.1. Science Technology Engineering Mathematics (STEM) 13 2.2. Text Clustering 14 2.3. Text Classification 15 2.3.1. Support Vector Machine (SVM) 16 2.3.2. Naïve Bayes Classifier (NB) 17 2.3.3. Deep Learning 17 2.4. Topic Modeling 24 2.5. Summary of Literature Review 26 Chapter 3. Research Methodology 27 3.1. Research Framework 27 3.2. Data Collection and Preprocess Module 28 3.3. Question Clustering Module 29 3.4. Text Classification Module 31 3.4.1. Word Representation 32 3.4.2. Question Classification 36 3.5. Topic Modeling Module 43 3.6. Summary of Research Methodology 46 Chapter 4. Implementation and Verification 48 4.1. System Establishment 48 4.2. Implementation Methods 49 4.2.1. Dataset 50 4.2.2. Evaluation Standard 50 4.3. Parameter Setting 53 4.3.1. Cluster Number 53 4.3.2. Word Embedding Dimension 56 4.3.3. The Length of the Question Title and Question Contents 56 4.3.4. Parameters of Neural Network 57 4.3.5. Parameter of the Topic Number 57 4.4. Experiment Result and Analysis 58 4.4.1. Experiment 1 58 4.4.2. Experiment 2 60 4.4.3. Experiment 3 61 4.4.4. Experiment 4 62 Chapter 5. Discussion and Conclusion 64 5.1. Research Result 64 5.2. Future Work 68 Reference 69

    Andrews, R., Diederich, J., & Tickle, A. (1995). Survey and Critique of Techniques for Extracting Rules from Trained Artificial Neural Networks. Knowledge-based systems, 8(6), 373-389.
    Bagiati, A., Yoon, S., Evangelou, D., & Ngambeki, I. (2010). Engineering Curricula in Early Education: Describing the Landscape of Open Resources. Early Childhood Research & Practice, 12(2), n2.
    Bentley, J., & Friedman, J. (1978). Fast Algorithms for Constructing Minimal Spanning Trees in Coordinate Spaces. IEEE Transactions on Computers(2), 97-105.
    Berkling, K., & Lavalley, R. (2018). Automatic Orthographic Error Tagging and Classification for German Texts. Computer Speech & Language, 52, 56-78.
    Bessenyei, I. (2008). Learning and Teaching in the Information Society. Elearning 2.0 and Connectivism. Information Society, R. Pinter (Ed), Ed. Gondolat, 9, 1-14.
    Blei, D., & Lafferty, J. (2009). Topic Models. In Text Mining (pp. 101-124): Chapman and Hall/CRC.
    Blei, D., Ng, A., & Jordan, M. (2003). Latent Dirichlet Allocation. Journal of machine learning research, 3(Jan), 993-1022.
    Board, S. S., & Council, N. R. (2007). Earth Science and Applications from Space: National Imperatives for the next Decade and beyond: National Academies Press.
    Burke, L., & McNeill, J. (2011). Educate to Innovate: How the Obama Plan for STEM Education falls Short. Backgrounder, 2504, 1-8.
    Bybee, R. (2010). Advancing STEM Education: A 2020 Vision. Technology and engineering teacher, 70(1), 30.
    Bybee, R., & Fuchs, B. (2006). Preparing the 21st century Workforce: A New Reform in Science and Technology Education. Journal of Research in Science Teaching: The Official Journal of the National Association for Research in Science Teaching, 43(4), 349-352.
    Carmona, C., Castillo, G., & Millán, E. (2007). Discovering Student Preferences in E-learning. Paper presented at the Proceedings of the international workshop on applying data mining in e-learning.
    Carnevale, A., Smith, N., & Melton, M. (2011). STEM: Science Technology Engineering Mathematics. Georgetown University Center on Education and the Workforce.
    Chang, K., Sung, Y., & Chen, I. (2002). The Effect of Concept Mapping to Enhance Text Comprehension and Summarization. The Journal of Experimental Education, 71(1), 5-23.
    Chen, X. (2009). Students Who Study Science, Technology, Engineering, and Mathematics (STEM) in Postsecondary Education. Stats in Brief. NCES 2009-161. National Center for Education Statistics.
    Chen, X., Hu, X., Lim, T., Shen, X., Park, E., & Rosen, G. (2011). Exploiting the Functional and Taxonomic Structure of Genomic Data by Probabilistic Topic Modeling. IEEE/ACM transactions on computational biology and bioinformatics, 9(4), 980-991.
    Conti, D., & GIBERTa’b, K. (2012). The Use of the Traffic Lights Panel as a Goodness-of-Clustering Indicator an Application to Financial Assets. Paper presented at the Artificial Intelligence Research and Development: Proceedings of the 15th International Conference of the Catalan Association for Artificial Intelligence.
    Cui, X., & Potok, T. (2005). Document Clustering Analysis based on Hybrid PSO+ K-means Algorithm. Journal of Computer Sciences (special issue), 27, 33.
    Deerwester, S., Dumais, S., Furnas, G., Landauer, T., & Harshman, R. (1990). Indexing by Latent Semantic Analysis. Journal of the American society for information science, 41(6), 391-407.
    DeJarnette, N. (2012). America's Children: Providing Early Exposure to STEM (Science, Technology, Engineering and Math) Initiatives. Education, 133(1), 77-84.
    Downes, S. (2005). E-learning 2.0. Elearn magazine, 2005(10), 1.
    Esuli, A., & Sebastiani, F. (2009). Active Learning Strategies for Multi-Label Text Classification. Paper presented at the European Conference on Information Retrieval.
    Goldberg, Y., & Levy, O. (2014). Word2vec Explained: Deriving Mikolov et al.'s Negative-Sampling Word-Embedding Method. arXiv preprint arXiv:1402.3722.
    Government, U. S. (2006). Human Trafficking: Better Data, Strategy, and Reporting Needed to Enhance US Antitrafficking Efforts Abroad: DIANE Publishing.
    Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A., Jaitly, N., . . . Sainath, T. (2012). Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups. IEEE Signal processing magazine, 29(6), 82-97.
    Hofmann, T. (1999). Probabilistic Latent Semantic Analysis. Paper presented at the Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence.
    Holla, S., & Katti, M. (2012). Android based Mobile Application Development and its Security. International Journal of Computer Trends and Technology, 3(3), 486-490.
    Hung, H., & Cho, V. (2008). Continued Usage of E‐learning Communication Tools: a Study from the Learners' Perspective in Hong Kong. International Journal of Training and Development, 12(3), 171-187.
    Islam, R., Islam, R., & Mazumder, T. (2010). Mobile Application and its Global Impact. International Journal of Engineering & Technology (IJEST), 10(6), 72-78.
    J., W., & H., J. (1963). Hierarchical Grouping to Optimize an Objective Function. Journal of the American statistical association, 58(301), 236-244.
    Jaderberg, M., Simonyan, K., & Zisserman, A. (2015). Spatial Transformer Networks. Paper presented at the Advances in Neural Information Processing Systems.
    Jagarlamudi, J., Daumé III, H., & Udupa, R. (2012). Incorporating Lexical Priors into Topic Models. Paper presented at the Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics.
    Jain, A., Murty, M., & Flynn, P. (1999). Data Clustering: a Review. ACM computing surveys (CSUR), 31(3), 264-323.
    Kadry, S., & El Hami, A. (2016). E-Learning 3.0: Technologies, Applications, Benefits, Trends, and Challenges. In E-Systems for the 21st Century (pp. 123-194): Apple Academic Press.
    Kim, H., & Yoon, C. (2004). Determinants of Subscriber Churn and Customer Loyalty in the Korean Mobile Telephony Market. Telecommunications Policy, 28(9-10), 751-765.
    Kim, Y. (2014). Convolutional Neural Networks for Sentence Classification. arXiv preprint arXiv:1408.5882.
    Kolb, A., & Kolb, D. (2005). Learning Styles and Learning Spaces: Enhancing Experiential Learning in Higher Education. Academy of management learning & education, 4(2), 193-212.
    Kwyk. (2017). A non-NLP application of Word2Vec. Retrieved from https://towardsdatascience.com/a-non-nlp-application-of-word2vec-c637e35d3668
    Lacoste, J., Perin, C., & Jobard, B. (2008). Progressive Transmission of Appearance Preserving Octree-Textures. Paper presented at the Proceedings of the 13th international symposium on 3D web technology.
    Lakhan, S., & Jhunjhunwala, K. (2008). Open Source Software in Education. Educause Quarterly, 31(2), 32.
    Lau, R., Xia, Y., & Ye, Y. (2014). A Probabilistic Generative Model for Mining Cybercriminal Networks from Online Social Media. IEEE Computational intelligence magazine, 9(1), 31-43.
    Levesque, D., & Kelly, G. (2002). Meeting the Challenge of continuing Education with ELearning. Radiology management, 24(2), 40-43.
    Li, Y., Wei, B., Liu, Y., Yao, L., Chen, H., Yu, J., & Zhu, W. (2018). Incorporating Knowledge into Neural Network for Text Representation. Expert Systems with Applications, 96, 103-114.
    Lim, W., So, H., & Tan, S. (2010). ELearning 2.0 and New Literacies: are Social Practices Lagging Behind? Interactive Learning Environments, 18(3), 203-218.
    Lu, Y., Mei, Q., & Zhai, C. (2011). Investigating Task Performance of Probabilistic Topic models: an empirical study of PLSA and LDA. Information Retrieval, 14(2), 178-203.
    MacQueen, J. (1967). Some Methods for Classification and Analysis of Multivariate Observations. Paper presented at the Proceedings of the fifth Berkeley symposium on mathematical statistics and probability.
    Mcauliffe, J., & Blei, D. (2008). Supervised Topic Models. Paper presented at the Advances in Neural Information Processing Systems.
    Mikolov, T., Le, Q., & Sutskever, I. (2013). Exploiting Similarities among Languages for Machine Translation. arXiv preprint arXiv:1309.4168.
    Miles, M., Saxl, E., & Lieberman, A. (1988). What Skills do Educational “Change Agents” Need? An Empirical View. Curriculum Inquiry, 18(2), 157-193.
    Miranda, P., Isaias, P., & Costa, C. (2014). E-Learning and Web generations: Towards Web 3.0 and E-Learning 3.0. International Proceedings of Economics Development and Research, 81, 92.
    Murtagh, F. (1983). A Survey of Recent Advances in Hierarchical Clustering Algorithms. The Computer Journal, 26(4), 354-359.
    Murtagh, F., & Legendre, P. (2014). Ward’s Hierarchical Agglomerative Clustering Method: which Algorithms Implement Ward’s Criterion? Journal of classification, 31(3), 274-295.
    Naili, M., Chaibi, A., & Ghezala, H. (2017). Comparative Study of Word Embedding Methods in Topic Segmentation. Procedia Computer Science, 112, 340-349.
    Pennington, J., Socher, R., & Manning, C. (2014). Glove: Global Vectors for Word Representation. Paper presented at the Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP).
    Rohlf, F. (1978). A Probabilistic Minimum Spanning Tree Algorithm. Inf. Process. Lett., 7(1), 44-48.
    Romiszowski, A. (2004). How's the E-learning Baby? Factors leading to Success or Failure of an Educational Technology Innovation. EDUCATIONAL TECHNOLOGY-SADDLE BROOK THEN ENGLEWOOD CLIFFS NJ-, 44(1), 5-27.
    Sanders, M. (2008). Stem, Stem Education, Stemmania.
    Stent, A., Marge, M., & Singhai, M. (2005). Evaluating Evaluation Methods for Generation in the Presence of Variation. Paper presented at the International Conference on Intelligent Text Processing and Computational Linguistics.
    Steyvers, M., & Griffiths, T. (2007). Probabilistic Topic Models. Handbook of latent semantic analysis, 427(7), 424-440.
    Vinayakumar, R., Soman, K., & Poornachandran, P. (2017). Deep Android Malware Detection and Classification. Paper presented at the 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI).
    Wang, H., Hsu, T., & Sari, Y. (2019). Personal Research Idea Recommendation using Research Trends and a Hierarchical Topic Model. Scientometrics, 121(3), 1385-1406.
    Wang, P., Xu, B., Xu, J., Tian, G., Liu, C., & Hao, H. (2016). Semantic Expansion using Word Embedding Clustering and Convolutional Neural Network for Improving Short Text Classification. Neurocomputing, 174, 806-814.
    Wang, S., & Manning, C. (2012). Baselines and Bigrams: Simple, Good Sentiment and Topic Classification. Paper presented at the Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers-Volume 2.
    Wang, T., Cai, Y., Leung, H., Lau, R., Li, Q., & Min, H. (2014). Product Aspect Extraction Supervised with Online Domain Knowledge. Knowledge-based systems, 71, 86-100.
    Wang, X., & McCallum, A. (2005). A Note on Topical N-grams. Retrieved from
    Wei, X., & Croft, W. (2006). LDA-based Document Models for Ad-hoc Retrieval. Paper presented at the Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval.
    Wikipedia. (2018a). Artificial neural network. Retrieved from https://en.wikipedia.org/wiki/Artificial_neural_network
    Wikipedia. (2018b). Convolutional Neural Network. Retrieved from https://en.wikipedia.org/wiki/Convolutional_neural_network
    Wikipedia. (2018c). Deep Learning. Retrieved from https://en.wikipedia.org/wiki/Deep_learning
    Wikipedia. (2018d). Naive Bayes Classifier (NB). Retrieved from https://en.wikipedia.org/wiki/Naive_Bayes_classifier
    Wikipedia. (2018e). Support Vector Machine (SVM). Retrieved from https://en.wikipedia.org/wiki/Support_vector_machine
    Wikipedia. (2018f). Topic Modeling. Retrieved from https://en.wikipedia.org/wiki/Topic_model
    Wikipedia. (2018g). Word Embedding. Retrieved from https://en.wikipedia.org/wiki/Word_embedding
    Wilmink, F., & Uytterschaut, H. (1984). Cluster Analysis, History, Theory and Applications. In Multivariate Statistical Methods in Physical Anthropology (pp. 135-175): Springer.
    Yim, O., & Ramdeen, K. (2015). Hierarchical Cluster Analysis: Comparison of Three Linkage Measures and Application to Psychological Data. The quantitative methods for psychology, 11(1), 8-21.

    下載圖示
    2025-02-06公開
    QR CODE