跳到主要內容

臺灣博碩士論文加值系統

(18.97.9.172) 您好!臺灣時間:2025/02/11 14:45
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:范詠甯
研究生(外文):FAN,YONG-NING
論文名稱:機器學習於財務資訊系統需求分類之研究
論文名稱(外文):A Study on Machine Learning for System Requirements Classification in Financial Information System
指導教授:禹良治禹良治引用關係
指導教授(外文):YU, LIANG-CHIH
口試委員:林俊杰許嘉裕
口試委員(外文):LIN, JYUN-JIEHSU, CHIA-YU
口試日期:2022-06-28
學位類別:碩士
校院名稱:元智大學
系所名稱:資訊管理學系
學門:電算機學門
學類:電算機一般學類
論文種類:學術論文
論文出版年:2022
畢業學年度:110
語文別:中文
論文頁數:44
中文關鍵詞:需求分類文字探勘機器學習
外文關鍵詞:Requirements ClassificationText MiningMachine Learning
相關次數:
  • 被引用被引用:0
  • 點閱點閱:187
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
企業內部資訊系統上線後,當用戶有系統相關問題與需求時,需人工進行分類、建檔與指派工作等作業,若能將智能客服概念整合後端分類器功能,並導入企業內部資訊系統,將系統需求自動化分類。對於資訊部門來說,能快速呈現資訊系統主要問題,以及達到簡化作業流程;對用戶來說,能立即獲取答覆,及有效地縮短處理的等待時間,只要善加運用與規劃,將能達到企業端與用戶端雙贏局面。

本研究以「財務資訊系統」需求為例,運用文字探勘的方法應用在資料處理與分析上。首先利用R語言來完成自然語言技術的處理,以取得TF-IDF權重數表示的訓練樣本,再以機器學習(WEKA)應用軟體使用支持向量機序列最小最佳化(SMO)、樸素貝葉斯(Naive Bayes)、決策樹(Decision Tree)、隨機森林(Random Forest)等四種演算法進行分類建模測試。實驗結果,100維重新取樣使用隨機森林為分類效能最佳的模型,所取得的綜合評價指標(F-measure)值為94.5%。

After the company's internal information system is launched, when users have system-related problems and needs, they need to manually classify content, create files and assign tasks. If the intelligent customer service concept can be integrated with the back-end classifier function, and imported into the company's internal information system, to automatically classify system requirements. For the IT department, it can quickly present the main problems of the information system and simplify the operation process; for the user, it can get the answer immediately and effectively shorten the waiting time for processing. A win-win situation between the client and the user.

This study takes the system requirement of "financial information system" as an example, and applies the method of text mining to data processing and analysis. First, use R language to complete the processing of natural language technology to obtain training samples represented by TF-IDF, and machine learning (WEKA) to perform classification modeling tests using SMO, Naive Bayes, decision tree, and Random Forest. Experimental results,100-dimensional resample and using random forest as the best model for classification performance, the F-measure obtained is 94.5%.

書頁名...i
論文口試委員審定書...ii
中文摘要...iii
英文摘要...iv
誌謝...v
目錄...vi
表目錄...viii
圖目錄...x
第一章 緒論...1
1.1研究背景與動機...1
1.2研究目的...2
1.3論文架構...3
第二章 文獻探討...5
2.1文字探勘(Text Mining)...5
2.2自然語言處理(Natural Language Processing)...5
2.3詞頻-逆向文件頻率(Term Frequency-Inverse Document Frequency)...6
2.4十折交叉驗證(10-fold cross-validation)...7
第三章 研究規劃...8
3.1研究架構...8
3.2研究流程...9
3.2.1 蒐集資料...9
3.2.2 資料前置處理...11
3.2.3 分類建模測試...15
3.2.4 評估與分析...16
第四章 實驗與分析...20
4.1模擬實驗...20
4.2可行性評估與檢討...24
4.3實驗流程檢討...26
4.4正式實驗...28
4.5實驗結果...29
4.5.1原始取樣(None)...29
4.5.2重新取樣(Resample)...31
4.6評估與分析...33
第五章 研究結論暨未來展望...40
5.1研究結論...40
5.2未來展望...41
參考文獻...43

[1] 劉冠麟,機器學習分類防疫新聞,國立中央大學通訊工程學系碩士論文,2020。
[2] 戴穎璁,最適自然語言處理之文件分割型式-應用於工程文件關鍵字萃取,國立金門大學土木與工程管理學系碩士論文,2021。
[3] 徐捷,機器學習於社群媒體國軍申訴分類之研究,元智大學資訊管理學系碩士論文,2021。
[4] 黃偉倫,機器學習於軍紀案件分類之研究,元智大學資訊管理學系碩士論文,2021。
[5] 黃莠娟,應用文件分類技術於服務需求分析之研究,元智大學資訊管理學系碩士論文,2013。
[6] 袁梅宇,WEKA機器學習與大數據聖經(第3版),佳魁資訊,2017。
[7] 陳怡廷,「從公司與顧客的認知價值初探企業潛在無形資產:以自然語言處理的方法為應用」,中山管理評論,24 卷3期:565~608,2016。
[8] 曾元顯,"自動化資訊組織與主題分析近二十年來的研究與發展", 教育資料與圖書館學,51:3~26,2014。
[9] Ya-Min Chou and Chu-Ren Huang,"異體字語境關係的分析與建立 (A Framework for the Contextual Analysis of Chinese Characters Variants)[In Chinese]" ,Proceedings of the 17th Conference on Computational Linguistics and Speech Processing,pp. 273-291,2005。
[10] Lokesh S. Katore and Jayant S. Umale, "Comparative Study of Recommendation Algorithms and Systems Using WEKA," International Journal of Computer Applications, Volume 110 , No. 3, 2015.
[11] Mark Hall, Eibe Frank, Geoffrey Holmes, Bernhard Pfahringer, Peter Reutemann, and Ian H. Witten, "The WEKA Data Mining Software: An Update," SIGKDD Explorations, Volume 11, Issue 1, 2009.
[12] Eibe Frank, Mark A. Hall, and Ian H. Witten, "The WEKA Workbench. Online Appendix for Data Mining: Practical Machine Learning Tools and Techniques," Morgan Kaufmann, Fourth Edition, 2016.
[13] Chris Manning and Hinrich Schütze, "Foundations of Statistical Natural Language Processing," MIT Press. Cambridge, MA, 1999.
[14] Yue Zhang and Zhiyang Teng, "Natural Language Processing: A Machine Learning Perspective," Cambridge: Cambridge University Press, 2021.
[15] Wei-Yun Ma and Keh-Jiann Chen, "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 (SIGHAN-03), pp. 168-171, 2003.
[16] Bo Pang and Lillian Lee, "Opinion mining and sentiment analysis ,"Foundations and trends in information retrieval, vol. 2, no. 1-2, pp. 1-135, 2008.
[17] Rafael A. Calvo and Sidney D'Mello, "Affect detection: An interdisciplinary review of models, methods, and their applications," IEEE Trans. Affective Computing, vol. 1, no. 1, pp. 18-37, 2010.
[18] Ronen Feldman, "Techniques and applications for sentiment analysis,"Communications of the ACM, vol. 56, no. 4, pp. 82-89, 2013.
[19] C. Lakshmi Devasena and M. Hemalatha, "Automatic Text categorization and summarization using rule reduction," IEEE-International Conference On Advances In Engineering, Science And Management (ICAESM -2012), pp. 594-598, 2012.

電子全文 電子全文(網際網路公開日期:20270101)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊