應用智慧分類法提升文章發佈效率於一企業之知識分享平台

Applying Intelligence Classification to Enhance Article Publishing Efficiency on A Knowledge Sharing Platform

詹智鈞(Chih-Chun Chan)

指導教授 ： 楊鎮華

國立中央大學/資訊電機學院/資訊工程學系碩士在職專班/碩士(2010年)

摘要

文件在進行分類處理時，除了需要花費時間閱讀以瞭解其內容主題，有時候可能也需要俱備一定的專業知識才能理解文件內容，因此文件分類是一件相當花費時間且需要特定的專家才能完成的一項工作，在資訊化已相當普及的今天，文件資料儲存的平台與讀者的閱讀習慣從紙本書籍轉換到數位資料上，因此如何利用電腦運算處理自動化的優勢來解決分類問題的重要性也日益增加，以節省文件分類的時間與降低人工分類的困難度。
本研究應用SVM分類器於一企業的知識分享平台的文件發佈流程中，並以其由人工進行分類好的文件分類做為測試資料進行分類效能評測，測試文件性質為來自產業情報網站上的科技產業新聞文章，由實驗結果發現SVM分類器在此類文件的分類準確率達到86%，在處理多類別分類的問題時也達到86%的準確度，因此SVM分類器很適合應用在此類科技產業新聞文件的分類處理。

關鍵字

文件分類 ； 文件發佈 ； 支援向量機

並列摘要

During processing the document classification, in addition to takes time for reading to understand the document content, sometimes also need some expertise to understand the document content. Therefore, document classification is a work which is very time consuming and requires specific experts to complete. Nowadays, information technology has been quite popular, and the documents storage platform and the reading habits of readers had changed from paper to digital content. Accordingly, the importance of how to use the advantages of computing process automation to solve the classification problem is getting increasingly, so that to save time and reduce the difficulties of artificial document classification.
In this study, we applied SVM classifier in a knowledge sharing platform for enterprise document publishing process, and use its classified documents processed by document publisher as our experiment testing data. The documents gathered from the technology industry news articles. The experiment results of SVM classifier in the classification accuracy rate is 86%, in dealing with the case of multi-class classification is also 86% accuracy. Hence, the SVM classifier is suitable for applications in such technology industry news articles document classification.

並列關鍵字

Article publishing ； SVM ； Document classification

參考文獻

Anette Hulth., & Beata B. Megyesi. (2006). A Study on Automatically Extracted Keywords in Text Categorization.

Arunkumar Chinnasamy., Wing-Kin Sung., & Ankush Mittal. (2005). Protein Structure and Fold Prediction Using Tree-augmented Naïve Bayesian Classifier. J.BioInformatics and Computational Biology 3 (4), 803-820

Chih-Chung Chang., & Chih-Jen Lin. (2001). LIBSVM : a library for support vector machines.

Corinna Cortes., & V. Vapnik. (1995). Support-Vector Networks. Machine Learning, 20.

G. Salton., & C. S. Yang. (1973). On the Specification of Term Values in Automatic Indexing, Journal of Documentation, 29(4), 351-372.