請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74459
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 周瑞仁(Jui-Jen Chou) | |
dc.contributor.author | Sin Lian | en |
dc.contributor.author | 連鑫 | zh_TW |
dc.date.accessioned | 2021-06-17T08:36:59Z | - |
dc.date.available | 2024-08-13 | |
dc.date.copyright | 2019-08-13 | |
dc.date.issued | 2019 | |
dc.date.submitted | 2019-08-08 | |
dc.identifier.citation | 曾秋旺。2018。教學問卷文字意見探勘應用於優良教師之遴選。碩士論文。台北: 臺灣大學生物產業機電工程學研究所。
Bengio, Y., P. Simard, and P. Frasconi. 1994. Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks 5(2): 157-166. Collobert, R., and J. Weston. 2008. A Unified Architecture For Natural Language Processing: Deep Neural Networks With Multitask Learning. In 'Proc. 25th International Conference on Machine Learning.', 160-167. Dutt, A., M. A. Ismail, and T. Herawan. 2017. A Systematic Review on Educational Data Mining. IEEE Access 5:15991-16005. Hochreiter, S., and J. Schmidhuber. 1997. Long Short-term Memory. Neural computation (9)8: 1735-1780. Jieba. 2013. Chinese Text Segmentation. Available at http://github.com/fxsjy/jieba. Accessed on Aug. 30, 2017. Lei, Z., W. Shuai, and L. Bing. 2018. Deep learning for Sentiment Analysis: A Survey. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 8(4): e1253. Luong, M. T., H. Pham, and C. D. Manning. 2015. Effective Approaches to Attention-based Neural Machine Translation. arXiv preprint arXiv: 1508.04025. Mikolov, T., W. Yih, and G. Zweig. 2013. Linguistic Regularities in Continuous Space Word Representations. 'Proc. of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies', 746-751. Nabeela, A., C. Mihaela, and F. Sanaz. 2014. Sentiment Analysis: Towards a Tool for Analysing Real-time Students Feedback. In: 2014 IEEE 26th international Conference on Tools With Artificial Intelligence., 419-423. Olah, C. 2015. Understanding LSTM Networks. Available at http://colah.github.io/posts/2015-08-Unders-tanding-LSTMs/. Accessed on Nov. 10. Peng, H., E. Cambria, and A. Hussain. 2017. A review of sentiment analysis research in Chinese language. Cognitive Computation, 9(4): 423-435. Ranjan, J., and K. Malik. 2007. Effective Educationl Proess: a Data-mining Approach. Vine 37(4): 502-515. Romero, C., and S. Ventura. 2010. Educational Data Mining: a Review of the state of the Art. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 0(6): 601-618. Schuster, M., and K. K. Paliwal. 1997. Bidirectional Recurrent Neural Networks. IEEE Transactions on Signal Processing, 45(11): 2673-2681. Sujata, R., and K. Parteek. 2017. A sentiment Analysis System to Improve Teaching and Learning. Computer, 50(5): 36-43. Xu, Y. K. T., D. Chitsaz, R. A. Brown, Q. L. Cui, M. A. Dabarno, J. P. Antel, and T. E. Kennedy. 2019. Deep Learning for High-throughput Quantification of Oligodendrocyte Ensheathment at Single-cell Resolution. Communications Biology, 2(1): 116. Yue, L., W. Xutao, and X. Pengjian. 2018. Chinese Text Classification Model Based on Deep Learning. Future Internet, 10(11): 113. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74459 | - |
dc.description.abstract | 本研究與國立宜蘭大學校務研究辦公室合作,針對教學問卷文字意見進行文字情緒分析,並將結果分別應用於教師教學之反饋與優良教師之遴選。教師教學可由學生教學問卷得到回饋,惟需花費大量人力及時間進行意見提取,因此本研究開發一套系統,進行學生教學問卷文字意見分析的自動化,及時提供教師教學之參考並進而檢討改進,以及提供優良教師遴選之參考。
本研究利用資料探勘方法來對教學問卷進行質性評估。接著對教學問卷文字意見進行資料前處理並給予正面、中性及負面情緒的標註,之後將其向量化與分析。本研究比較循環神經網路、長短期記憶、專注循環神經網路、專注長短期記憶及卷積神經網路五種分類模型之文字情緒性能,最後選出最適合的分類器。 經各模型之分析性能比較後,從少量詞組去進行特徵提取效果較佳。本研究推薦卷積神經網路來作為教師教學改善及優良教師遴選目標之分類器,其分別於非負面情緒辨識率達96.0%,以及負面情緒辨識率達94.2%;於非正面情緒辨識率達94.1%,以及正面情緒辨識率達95.9%。 | zh_TW |
dc.description.abstract | The study was conducted in collaboration with the office of Institutional Research (IR) at National Ilan University (NIU) in Taiwan to analyze textual opinions in teaching evaluation questionnaires, then apply the analysis results to the teaching of teachers and the selection of outstanding teachers. Teachers’ teaching can be awarded by the teaching evaluation questionnaires, but it takes a lot of manpower and time to extract the students’ opinions. Therefore, the research develops a set of system to automate the analysis of textual opinions in teaching evaluation questionnaires, not only providing reference for the improvement of teachers' teaching, but also providing a reference for outstanding teacher selection.
The study used data mining methods to qualitatively evaluate teaching questionnaires. First, the textual of the teaching questionnaire is pre-processed and labeled with positive, neutral and negative sentiments, then vectorized and analyzed. The study compared the textual sentiment performance of five kinds of classification models: Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Attention RNN, Attention LSTM and Convolutional Neural Network (CNN), and finally selected the most suitable classifier. We found that classifiers with a small number of phrases from feature extraction is better. Among those models CNN model has best performance with non-negative sentiment recognition rate of 96.0% and negative sentiment recognition rate of 94.2%, as well as non-positive sentiment recognition rate of 94.1%, and positive sentiment recognition rate of 95.9%. Thus, the study chose CNN as a classifier for teacher teaching improvement and outstanding teacher selection goals. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T08:36:59Z (GMT). No. of bitstreams: 1 ntu-108-R06631009-1.pdf: 3046303 bytes, checksum: 92c07af2b5d6dfec949cd6d51baac99c (MD5) Previous issue date: 2019 | en |
dc.description.tableofcontents | 口試委員審定書 i
致謝 Acknowledgements ii 摘要 iii Abstract iv 目錄 vi 圖目錄 viii 表目錄 x 第1章 前言 Introduction 1 第2章 文獻探討 Literature Review 3 2.1 資料探勘 Data Mining 3 2.2 教育資料探勘 Educational Data Mining 4 2.3 文字情緒分析 5 第3章 材料與方法 Materials and Methods 8 3.1 教學問卷內容 9 3.2 資料前處理 11 3.2.1 資料清理內容 12 3.3 文字情緒模型 13 3.3.1 文字轉向量 13 3.3.2 循環神經網路 15 3.3.3 長短期記憶 17 3.3.4 邏輯回歸 19 3.3.5 專注循環神經網路 21 3.3.6 卷積神經網路 22 3.4 效能評估 25 3.4.1 F1-score 25 3.4.2 AUC-ROC 26 3.4.3 參數量 28 3.4.4 訓練收斂時間及推論速度 28 第4章 結果與討論 Results and Discussion 30 4.1 資料前處理後結果 30 4.1.1 期中教學問卷 30 4.1.2 整體教學問卷 30 4.2 文字情緒分析 32 4.2.1 非負面及負面情緒分類效能 32 4.2.1.1. 字詞序列特徵提取差異 33 4.2.1.2. 分類成效 33 4.2.1.3. 參數量 37 4.2.1.4. 訓練收斂時間及推論速度 37 4.2.2 正面情緒與非正面情緒分類效能 39 4.2.2.1. 分類成效 39 4.2.2.2. 參數量 42 4.2.2.3. 訓練收斂時間及推論速度 43 第5章 結論 Conclusion 44 參考文獻 References 45 | |
dc.language.iso | zh-TW | |
dc.title | 應用深度學習於教學問卷之探勘與反饋 | zh_TW |
dc.title | Deep Learning Applied in Analysis of the Student Surveys for Feedback to Instructors | en |
dc.type | Thesis | |
dc.date.schoolyear | 107-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 陳倩瑜(Yun-Cheng Tsai),蔡芸琤(Chien-Yu Chen) | |
dc.subject.keyword | 教師教學反饋,優良教師遴選,教學問卷,文字情緒分析,卷積神經網路, | zh_TW |
dc.subject.keyword | Teacher teaching feedback,Selection of outstanding teachers,Teaching evaluation questionnaires,Text sentiment analysis,Convolution neural network, | en |
dc.relation.page | 47 | |
dc.identifier.doi | 10.6342/NTU201902868 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2019-08-10 | |
dc.contributor.author-college | 生物資源暨農學院 | zh_TW |
dc.contributor.author-dept | 生物產業機電工程學研究所 | zh_TW |
顯示於系所單位: | 生物機電工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-108-1.pdf 目前未授權公開取用 | 2.97 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。