臺灣博碩士論文加值系統

幼兒園是在人生成長的過程中的第一個小型社會，在集體的教育中，每個孩子擁有不同的性格，來自於不同的家庭背景，幼兒園也是學習與人相處和社會化的重要場域。而如今，隨著國人的教育水平逐漸提升，孩子的受教品質與教育環境在近年來被逐漸重視。縱然從事幼兒教育工作者在就職前已經過專業培訓，但當親臨實際工作環境時，現場發生的狀況可能很難依循傳統紙本教科書中的方法逐一執行，亦或許該狀況的處理方式不存在於書中。
伴隨科技的發展，受益於網際網路的進步，也使得現代人獲取知識的途徑以不受限於書本之中，藉由網路，人們可以更輕易且快速的獲取感興趣的知識，對於幼教工作者而言，亦可透過網路搜尋對於工作時所遇到的瓶頸之解決方法。然而，有利弊有弊，網路促使資訊快速增長，隨之而來也造成資訊的超載，這也造成幼教工作者在網路上搜尋相關案例時，需要耗費需多時間閱讀和過濾網路資料中的知識，隨著需要檢閱的資訊越來越多，也導致幼教工作者難以挑選適合自己的資源。
本研究利用文字探勘方法與視覺化來抽取詞彙關係，在專家提供的背景知識下，除了通過抽取特徵詞以檢視幼兒教育文章中的核心意義，也藉由共詞分析技術探討特徵詞之間的關聯性，並以視覺化方式呈現幼教領域特徵詞的群集以及領域中被熱門討論的議題。

Kindergarten is the first small society in the process of life growth. In the collective education, each child has a different family background and personality traits, the kindergarten is also important fields to learning to get along with people and socialization. Modern, with the gradual improvement of the educational level of the people in Taiwan, the quality of children's education and education environment have been gradually valued in recent years. Even though early childhood education workers have been professionally trained before they take up their jobs, although early childhood educators receive professional training prior to their employment, being in the actual working environment the situation is difficult to follow book methods or the handled way is not exist in the book.
With the development of technology, benefiting from the progress of the Internet, people's access to knowledge is not limited to books. Through the Internet, people can acquire the knowledge of interest more easily and quickly. For preschool educators, you can also search online for solutions to bottlenecks encountered at work. However, there are advantages and disadvantages, rapid growth of information generated by the Internet, which also leads to an overload of information, which also leads early childhood educators to spend more time reading and filtering searching on the Internet Knowledge in relevant cases online material, As more and more information needs to be reviewed, also makes it difficult for early childhood educators to choose the right resources for themselves.
This study uses text mining and visualization to extract vocabulary relationships. based on the background knowledge provided by experts, extracting characteristic words to examine the core significance of early childhood education articles, also by co-word analysis discusses the correlation between characteristic words and visually presents clusters of key words in early childhood education and the topics discussed in the field.

第一章 緒論 1
1.1 研究背景 1
1.2 研究動機 1
1.3 研究目的 3
1.4 論文架構 3
第二章 文獻探討 5
2.1 自然語言處理 5
2.2 文字探勘 7
2.3 中文斷詞處理 8
2.4 特徵詞擷取 9
2.5 特徵詞權重計算 10
2.5.1 詞袋模型 10
2.5.2 詞頻-逆向文檔頻率 10
2.5.3 字詞頻率 10
2.5.4 逆向文檔頻率 11
2.6 詞嵌入 12
2.6.1 One-hot Encoding 12
2.6.2 Word2Vec 13
2.7 共詞分析 14
第三章 研究方法 17
3.1 詞向量訓練流程 19
3.1.1 定義幼兒教育問題種類 19
3.1.2 訓練文本資料集 20
3.1.3 訓練資料前處理 20
3.1.4 Word2Vec模型訓練 21
3.2 特徵詞網絡可視化流程 24
3.2.1 文章預處理 24
3.2.2 詞向量表示 26
3.2.3 句子特徵與類別相似度計算與排序 28
3.2.4 特徵詞彙整 29
3.2.5 特徵詞篩選 30
3.2.6 形成共詞矩陣 30
3.2.7 特徵詞網絡視覺化 31
第四章 實驗結果與評估 33
4.1 實驗資料 33
4.2 模型相關參數設定 33
4.3 句子相似度計算 35
4.4 特徵詞篩選 39
4.5 特徵詞網絡視覺化 42
第五章 結論與未來工作 51
5.1 結論 51
5.2 未來工作 51
參考文獻 52

[1] 陳世榮（2015）。社會科學研究中的文字探勘應用: 以文意為基礎的文件分類及其問題。人文及社會科學集刊，27.4，683-718。
[2] 陳淑琴（1995）。 幼兒非社會性行為的成因與輔導策略探討。幼兒教育年刊， 8，135-150。
[3] 陳良駒、張正宏、陳日鑫（2010）。以特徵詞共現特性探討知識管理研究議題相關性--使用共詞與關聯法則分析。資訊管理學報，17.4，31-60。
[[4] 自然語言處理（無日期）。維基百科，檢自https://zh.wikipedia.org/wiki/自然語言處理
[5] Feldman, R., & Sanger, J. (2007). The text mining handbook: advanced approaches in analyzing unstructured data. Cambridge university press.
[6] Luque, C., Luna, J. M., Luque, M., & Ventura, S. (2019). An advanced review on text mining in medicine. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 9(3), e1302.
[7] Ferreira‐Mello, R., André, M., Pinheiro, A., Costa, E., & Romero, C. (2019). Text mining in education. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 9(6), e1332.
[8] Dzikovska, M., Steinhauser, N., Farrow, E., Moore, J., & Campbell, G. (2014). BEETLE II: Deep natural language understanding and automatic feedback generation for intelligent tutoring in basic electricity and electronics. International Journal of Artificial Intelligence in Education, 24(3), 284-332.
[9] Dikli, S. (2006). An overview of automated scoring of essays. The Journal of Technology, Learning and Assessment, 5(1).
[10] Leong, C. K., Lee, Y. H., & Mak, W. K. (2012). Mining sentiments in SMS texts for teaching evaluation. Expert Systems with Applications, 39(3), 2584-2589.
[11] Hajizadeh, E., Ardakani, H. D., & Shahrabi, J. (2010). Application of data mining techniques in stock markets: A survey. Journal of Economics and International Finance, 2(7), 109-118.
[12] Glancy, F. H., & Yadav, S. B. (2011). A computational model for financial reporting fraud detection. Decision Support Systems, 50(3), 595-601.
[13] Dong, W., Liao, S., & Liang, L. (2016). Financial statement fraud detection using text mining: A systemic functional linguistics theory perspective. In Pacific Asia Conference on Information Systems (PACIS). Association For Information System.
[14] Elshendy, M., & Fronzetti Colladon, A. (2017). Big data analysis of economic news: Hints to forecast macroeconomic indicators. International Journal of Engineering Business Management, 9, 1847979017720040.
[15] Sun Junyi.fxsjy/jieba:結巴中文分詞（2020）。檢自https://github.com/fxsjy/jieba
[16] Ma, W. Y., & Chen, K. J. (2003, July). Introduction to CKIP Chinese word segmentation system for the first international Chinese word segmentation bakeoff. In Proceedings of the second SIGHAN workshop on Chinese language processing (pp. 168-171).
[17] 中央研究院中文斷詞系統（2020）。檢自 https://github.com/ckiplab/ckiptagger
[18] Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781.
[19] Ding, Y., Chowdhury, G. G., & Foo, S. (2001). Bibliometric cartography of information retrieval research by using co-word analysis. Information processing & management, 37(6), 817-842.
[20] Cobo, M. J., López‐Herrera, A. G., Herrera‐Viedma, E., & Herrera, F. (2011). Science mapping software tools: Review, analysis, and cooperative study among tools. Journal of the American Society for information Science and Technology, 62(7), 1382-1402.
[21] Giannakos, M., Papamitsiou, Z., Markopoulos, P., Read, J., & Hourcade, J. P. (2020). Mapping child–computer interaction research through co-word analysis. International Journal of Child-Computer Interaction, 23, 100165.
[22] 楊長舜（2020）。應用文字探勘技術探索廠商競合關係–以離岸風電產業為例。國立中山大學資訊管理學系研究所碩士論文，高雄市。 取自https://hdl.handle.net/11296/8pr77e
[23] 苾淳楊（2018）。從「應變自然」到「社會應變」：以文字探勘方法檢視國內風災新聞的報導演變。教育資料與圖書館學，55，3。
[24] 鄭百勝（2003）。應用關聯規則建構具方向性之領域知識結構圖－以資訊管理領域為例。國立中山大學資管所碩士論文。