網路資訊檢索與文字探勘 (Web Information Retrieval and Text Mining)
Spring, 2007
Instructor: Hung-Yu Kao (高宏宇)
Email: hykao (at) mail. ncku. edu. tw
Office: 4281A Tel: 2757575 ext 62546
Office Hour: Tue. Wed. 2PM~4PM
visitors
[Announcement]
[2/19] 2/28照學校行事曆放假一天不用上課
[3/7] Pre-Quiz
[3/22] 投影片已經更換為白底範本,方便大家列印
[3/28] Project 1 has been announced. 4/24 Due
[3/29] 4/4學校校際活動週放假,停課一次
[4/16] 期末報告分組名單請於5/1日以前寄給助教,組別人數1-3人
[4/24] project1缺交名單:Q36951102(5/1 update), 請儘速補交
[4/24] 期末報告論文請從IR concept投影片最後一頁所開列表選擇2003年以後論文，若有不在範圍內的論文想報告請先與老師討論
[4/24] 論文報告預計從5/9開始(5/2公布報告schedule)，同學請盡早準備
[5/2] 論文報告schedule(最後更新 5/9 1pm)
[5/7] Project 2 has been announced. 6/5 5pm Due
[5/30] Project 3 has been announced. 6/28 5pm Due
[6/26] Project 3已交名單(First 3)
[6/29] 學期分數最遲將於7/3 6pm(hard)前在網頁上公布,公布後如有問題請在7/6 中午前找老師
[7/3] 學期分數有問題請在7/6 中午前找老師 
Syllabus
- Introduction
- Basic WWW Technologies
- Mathematical Background
- Web Information Retrieval
- Review on IR
- When IR meets Web
- Advanced Crawling Techniques
- Web Characteristics Analysis
- Web Graphs
- Text Analysis
- Link Analysis
- Misc
- Human Behavior on the Web
- Commerce on the Web
- Future Internet Technologies
Grading
- Projects: 65% (15%,15%,35% respectively)
- We have three coding projects in this course. You should propose your design, implement a workable system to demostrate, and prepare a report for most of them.
- The first two projects are technical projects, and the last one trends to a research one.
- The last one is a team-work project. The topic of the last project is not limited. Experiments should be included in this project. It also contains a result presentation (10%).
- Paper debate: 35% (20% for presentation, 15% for three turn's challenges)
- Each team should select one topic (not a paper) to present. When one team is reporting, the selected two teams should stand for the negative side to ask questions and show the disadvantages of presented papers.
- Participation: (extra)
Text Book & References
TA 卓威廷,唐浩倫 (Room 4244, nckuwir@gmail.com)