當讀者欲了解某一文獻文章之重點內容並試圖復現其細部作法時，其往往需要通覽整篇文章，並針對其所需之細部作法步驟以及其所認定之重點內容進行辨別與確認，反復研讀其所判定之重點內容與細部做法，理解文章所表達之意涵，接著，花費大量時間精力通篇閱讀整篇文獻文章，逐一篩選其所需要之文章內容，並將其所需要之內容標註出來。另一方面，文獻文章中包含大量與讀者所欲蒐集內容無關之冗餘內容，導致其難以迅速了解並抓取文章之重點核心與細部做法，同時花費了大量的時間判斷標記其所需之細部內容。致使讀者難以快速獲取其所需之資訊。因此，本研究乃規劃發展一套「以文獻內容為基礎之文章單元關係判定及視覺化模式」，以協助讀者快速獲取其所需之信息。
本研究所發展之「以文獻內容為基礎之文章單元關係判定及視覺化」乃包含「文獻內容結構解析」前置階段與「段落單元重點內容判定及視覺化」方法論。於「文獻內容結構解析」前置階段中，本研究乃先自網路環境蒐集數則文獻文章，解析各文獻內容所包含之段落單元特徵屬性，歸納各特徵屬性之表達方式及表達類型，接著按照各特徵屬性之表達方式建立詞庫，以利後續進行段落單元之特徵屬性擷取。之後，本研究乃以前置階段之結果為基礎發展一套「段落單元重點內容判定及視覺化」方法論，此方法論主要包含「段落單元特徵屬性擷取」、「段落單元關係判定」、「段落單元關聯性判定」、「段落單元關聯性視覺化呈現」等四大階段。其中，「段落單元特徵屬性擷取」階段乃將前置階段所建置之詞庫與各段落單元內容進行比對，以擷取各段落單元內容之特徵屬性；「段落單元關係判定」階段乃推論各段落單元之具體關係，以作為呈現重點內容之基礎；「段落單元關聯性判定」階段乃將文章段落之標記內容與文章主要內容進行關聯性判定，以利後續步驟的視覺化呈現；「段落單元重點內容之視覺化呈現」階段乃將一文獻內容中之段落單元重點內容以視覺化方式呈現，以協助讀者快速理解文獻內容中之重點內容，進而幫助讀者更好理解文獻內容。

When readers want to understand the key points of a document and attempt to replicate its detailed methods, they often need to read through the entire article. They identify and confirm the detailed steps and key points they need, repeatedly studying the identified key points and methods to comprehend the article's meaning. This process involves spending a significant amount of time and effort reading the whole document, selecting the required content, and marking it. On the other hand, the document contains a lot of redundant information unrelated to what the reader wants to collect, making it difficult to quickly grasp the core points and detailed methods of the article, while also taking a lot of time to determine and mark the required details. This makes it challenging for readers to quickly obtain the information they need. Therefore, this study plans to develop a "Document-Based Article Unit Relationship Determination and Visualization Model" to help readers quickly obtain the information they need.

摘要 I
ABSTRACT II
目錄 III
圖目錄 V
表目錄 VII
第一章、研究背景 1
1.1 研究動機與目的 1
1.2 研究流程 4
1.3 研究定位 7
第二章、文獻回顧 8
2.1 文獻文章特徵擷取 8
2.2 文章單元重點內容判定 12
第三章、以文獻內容為基礎之判定單元關係及視覺化模式 17
3.1 文獻文章內容解析 18
3.1.1 段落單元特徵屬性解析 19
3.1.2 段落單元特徵屬性表達方式解析 21
3.2 段落單元之特徵屬性擷取 29
3.3 段落單元關係判定階段 42
3.4 段落單元關聯性判定階段 44
3.5 段落單元關聯性視覺化呈現階段 59
第四章、績效驗證與分析 62
4.1 模式驗證方式說明 62
4.2 驗證結果分析 68
第五章、結論與未來展望 86
5.1 論文總結 86
5.2 未來發展 88
參考文獻 90
附錄A、文獻文章內容解析前置作業 92
附錄B、驗證資料說明 126
附錄C、模式於第二階段之各週期的績效驗證結果 158

1. Singhal, A., Simmons, M., & Lu, Z ，2016，“Text Mining Genotype-Phenotype Relationships from Biomedical Literature for Database Curation and Precision Medicine.” PLoS Computational Biology, 12(11), e1005017–e1005017.
2. Lupi, F., Mabkhot, M. M., Boffa, E., Ferreira, P., Antonelli, D., Maffei, A., Lohse, N., and Lanzetta, M.(2023).Automatic definition of engineer archetypes: A text mining approach, Computers in Industry, 152, 103996.
3. Ignaczak, L., Goldschmidt, G., Costa, C. A. D., & Righi, R. D. R. (2021). Text mining in cybersecurity: A systematic literature review. ACM Computing Surveys (CSUR), 54(7), 1-36.
4. Gonçalves, H. S., & Moro, S. (2023). On the economic impacts of COVID‐19: A text mining literature analysis. Review of Development Economics, 27(1), 375-394.
5. Spasic, I., Ananiadou, S., McNaught, J., & Kumar, A. (2005). Text mining and ontologies in biomedicine: making sense of raw text. Briefings in bioinformatics, 6(3), 239-251.
6. Gündoğan, E., & Kaya, M. (2022). Deep learning based conference program organization system from determining articles in session to scheduling. Information Processing & Management, 59(6), 103107.
7. Alami, N., Meknassi, M., En-nahnahi, N., El Adlouni, Y., & Ammor, O. (2021). Unsupervised neural networks for automatic Arabic text summarization using document clustering and topic modeling. Expert Systems with Applications, 172, 114652.
8. Leaman, R., Wei, C. H., Allot, A., & Lu, Z. (2020). Ten tips for a text-mining-ready article: how to improve automated discoverability and interpretability. Plos Biology, 18(6), e3000716.
9. Widiastuti, N. I. (2019, November). Convolution neural network for text mining and natural language processing. In IOP Conference Series: Materials Science and Engineering (Vol. 662, No. 5, p. 052010). IOP Publishing.
10. Lee, W. Y., Bachtiar, M., Choo, C. C., & Lee, C. G. (2019). Comprehensive review of Hepatitis B Virus‐associated hepatocellular carcinoma research through text mining and big data analytics. Biological Reviews, 94(2), 353-367.