![]() |
|
以作者查詢圖書館館藏 、以作者查詢臺灣博碩士 、以作者查詢全國書目 、勘誤回報 、線上人數:27 、訪客IP:18.188.203.142
姓名 顏承印(Cheng-Yin Yen) 查詢紙本館藏 畢業系所 資訊工程學系 論文名稱 應用文本分類提供以概念圖為基礎的學習資源推薦
(Applying Neural Network to provide learning resources recommendation based on concept map)相關論文 檔案 [Endnote RIS 格式]
[Bibtex 格式]
[相關文章]
[文章引用]
[完整記錄]
[館藏目錄]
至系統瀏覽論文 ( 永不開放)
摘要(中) 本研究以ilearning線上學習平台為基礎,透過蒐集該平台上之課綱、電子教材、簡報教材當作資料來源,進行文本分類,並依據概念圖來實現適性化學習教材推薦,提供授課教師進行介入干預。
教材之推薦依據將透過卷積神經網路(Convolution Neural Network,CNN)、多層感知器(Multi-Layer Perceptron,MLP)、長短期記憶(Long-Short Term Memory,LSTM)與支持向量機(Support Vector Machine,SVM)等幾種神經網路與傳統機器學習的方式建立章節分類模型,同時結合一個Enrichment Method解決教材文本數量缺少、內文不足的情況,希望透過此短文本分類模型,結合Blended Course課程,分析出授課教師在設計課綱及課程教材上的規劃思路,藉此建立智慧分類模型。
文本分類準確度將以accuracy、precision、recall及f1-score做為評估指標,實驗結果顯示,透過本研究的Enrichment Method處理過後,各個指標在大部分的分類模型上皆有所提升,其中又以CNN的進步比例最多,達到30%,而整體成效以MLP表現最好。
實驗對象經由本推薦流程的介入之後,透過T檢定測試,發現在進步成績上,有推薦的實驗組進步成績相對於無推薦的控制組進步成績是有顯著差異的。摘要(英) Based on the ilearning online learning platform, this study collects syllabus, online materials on the platform as source of data, to classify context of webpage, and implements appropriate learning recommendations based on concept maps, providing interventions.
The recommendation is rely on the results of classification model build by several deep learning neural network classification models, which comprise Convolutional Neural Network, Multi-Layer Perceptron, Long-Short Term Memory and Support Vector Machine.
We used a data enrichment method to solve the issue of lack of samples and insufficient text. We want to combine these short text classification models and the blended course (operating system) to analyze the idea of instructor in designing course syllabus so as to establish a wisdom classification model.
In this study, we used accuracy、precision、recall and f1-score to evaluate the outcome of classification model.
The experimental results show that after the Enrichment Method, most of the classification models have improved, where CNN has the highest proportion of progress, reaching 30%, and MLP has the best performance in overall.
With our recommendation, students’ progress has significant difference between control group and experimental group through T test.關鍵字(中) ★ 文本分類
★ 深度學習
★ 卷積神經網路
★ 多層感知器
★ 長短期記
★ 支持向量機關鍵字(英) ★ Text Classification
★ Deep Learning
★ Convolution Neural Network
★ Multi-Layer Perceptron
★ Long-Short Term Memory
★ Support Vector Machine論文目次 摘要 I
ABSTRACT II
圖目錄 V
表目錄 VI
一、 前言 1
二、 文獻探討 2
2.1 PCR (Principal Component Regression) 2
2.1.1 主成分分析(Principle Component Analysis, PCA) 3
2.1.2 多元線性回歸(Multiple Linear Regression, MLR) 3
2.2 SPRT (Sequential Probability Ratio Test) 3
2.3 信心指標(Confidencce Indicator) 4
2.4 資料重採樣(Data Resampling) 5
2.5 多元分類(Multiclass Classification) 6
2.5.1 卷積神經網路(Convolution Neural Network, CNN) 6
2.5.1.1 輸入層(Embedding Layer) 7
2.5.1.2 卷積層(Convolution Layer) 8
2.5.1.3 池化層(Pooling Layer) 8
2.5.1.4 全連接層(Fully Connected Layer) + Softmax Layer 9
2.5.2 多層感知器(Multi-Layer Perceptron, MLP) 9
2.5.2.1 A Single Neuron 9
2.5.2.2 Feedforward Neural Network 10
2.5.3 長短期記憶(Long-Short Term Memory, LSTM) 11
2.5.4 支持向量機(Support Vector Machine, SVM) 12
三、 研究方法 13
3.1 系統環境 13
3.2 系統架構 13
3.3 Early Prediction Model 14
3.3.1 Data Collection 14
3.3.1.1 學務系統 15
3.3.1.2 數位學習系統 15
3.3.2 Data Storage 15
3.3.2.1 學務系統 16
3.3.2.2 數位學習系統 16
3.3.3 Data Extraction 17
3.3.3.1 Feature Extraction 17
3.3.3.2 Model Construction 18
3.3.3.3 Evaluation indicator 19
3.3.4 Application 19
3.4 Resource Recommendation Strategy 20
3.4.1 Data Collection 20
3.4.1.1 OS syllabus 20
3.4.1.2 SPRT題庫 20
3.4.1.3 Concept Map 21
3.4.2 Data Extraction 22
3.4.3 Application 22
3.5 Text Classification Model 23
3.5.1 Data Collection 23
3.5.1.1 OS materials 23
3.5.1.2 Glossary 24
3.5.1.3 Stop Word List 24
3.5.2 Data Storage 24
3.5.3 Data Extraction 25
3.5.4 Application 26
四、 實驗設計 27
4.1 實驗一:風險預測分析 28
4.2 實驗二:文本分類效能比較 28
4.3 實驗三:推薦機制成效評估 29
五、 結果討論與未來研究 30
5.1 實驗一:風險預測分析 30
5.2 實驗二:文本分類效能比較 36
5.2.1 授課教材之分類結果比較 36
5.2.2 外部教材之分類結果比較 37
5.3 實驗三:推薦機制成效評估 38
5.3.1 103到106學年成績分佈顯著性檢定 38
5.3.2 106學年度控制組與實驗組之成績差異檢定 41
5.3.2.1 前測檢定 41
5.3.2.2 進步成績檢定 42
5.3.2.3 期中考成績檢定 43
六、 參考文獻 43參考文獻 Almatrafi, O., Johri, A., & Rangwala, H. (2018). Needle in a haystack: Identifying learner posts that require urgent response in MOOC discussion forums. Computers & Education, 118, 1-9.
Bhushan, S. B., & Danti, A. (2017). Classification of text documents based on score level fusion approach. Pattern Recognition Letters, 94, 118-126.
Chen, M., Jin, X., & Shen, D. (2011). Short text classification improved by learning multi-granularity topics. Paper presented at the IJCAI.
Dai, Z., Sun, A., & Liu, X.-Y. (2013). Crest: Cluster-based representation enrichment for short text classification. Paper presented at the Pacific-Asia Conference on Knowledge Discovery and Data Mining.
Gao, L., Zhou, S., & Guan, J. (2015). Effectively classifying short texts by structured sparse representation with dictionary filtering. Information Sciences, 323, 130-142.
Li, M., Pan, S., Zhang, Y., & Cai, X. (2016). Classifying networked text data with positive and unlabeled examples. Pattern Recognition Letters, 77, 1-7.
Liu, C., Wang, W., Tu, G., Xiang, Y., Wang, S., & Lv, F. (2017). A new Centroid-Based Classification model for text categorization. Knowledge-Based Systems, 136, 15-26.
Lu, S.-H., Chiang, D.-A., Keh, H.-C., & Huang, H.-H. (2010). Chinese text classification by the Naïve Bayes Classifier and the associative classifier with multiple confidence threshold values. Knowledge-Based Systems, 23(6), 598-604.
Mizzaro, S., Pavan, M., Scagnetto, I., & Valenti, M. (2014). Short text categorization exploiting contextual enrichment and external knowledge. Paper presented at the Proceedings of the first international workshop on Social media retrieval and analysis.
Pang, G., & Jiang, S. (2013). A generalized cluster centroid based classifier for text categorization. Information Processing & Management, 49(2), 576-586.
Pinheiro, R. H., Cavalcanti, G. D., & Tsang, R. (2017). Combining dissimilarity spaces for text categorization. Information Sciences, 406, 87-101.
Sang, L., Xie, F., Liu, X., & Wu, X. (2016). WEFEST: word embedding feature extension for short text classification. Paper presented at the Data Mining Workshops (ICDMW), 2016 IEEE 16th International Conference on.
Silva, R. M., Almeida, T. A., & Yamakami, A. (2017). MDLText: An efficient and lightweight text classifier. Knowledge-Based Systems, 118, 152-164.
Tang, J., Wang, X., Gao, H., Hu, X., & Liu, H. (2012). Enriching short text representation in microblog for clustering. Frontiers of Computer Science, 6(1), 88-101.
Wang, P., Zhang, H., Xu, B., Liu, C., & Hao, H. (2014). Short text feature enrichment using link analysis on topic-keyword graph Natural Language Processing and Chinese Computing (pp. 79-90): Springer.
Williams, T. P., & Gong, J. (2014). Predicting construction cost overruns using text mining, numerical data and ensemble classifiers. Automation in Construction, 43, 23-29.
Xu, J., Wang, P., Tian, G., Xu, B., Zhao, J., Wang, F., & Hao, H. (2015). Short Text Clustering via Convolutional Neural Networks. Paper presented at the VS@ HLT-NAACL.
Xu, Z., Li, P., & Wang, Y. (2012). Text classifier based on an improved SVM decision tree. Physics Procedia, 33, 1986-1991.
Yang, B., Zhang, Y., & Li, X. (2011). Classifying text streams by keywords using classifier ensemble. Data & Knowledge Engineering, 70(9), 775-793.
Youn, E., & Jeong, M. K. (2009). Class dependent feature scaling method using naive Bayes classifier for text datamining. Pattern Recognition Letters, 30(5), 477-485.
Zhang, L., Jiang, L., Li, C., & Kong, G. (2016). Two feature weighting approaches for naive Bayes text classifiers. Knowledge-Based Systems, 100, 137-144.
Zheng, C. T., Liu, C., & San Wong, H. (2018). Corpus-based topic diffusion for short text clustering. Neurocomputing, 275, 2444-2458.指導教授 楊鎮華 審核日期 2018-7-13 推文 plurk
funp
live
udn
HD
myshare
netvibes
friend
youpush
delicious
baidu
網路書籤 Google bookmarks
del.icio.us
hemidemi
myshare