Email: tian@dr.com http://www.digiark.com/tian
Web Mining " "
WWW
Web URL Internet
WWW? (Search Engine), WWW
Internet WWW Yahoo http://www.yahoo.com/ InfoSeek http://www.infoseek.com/ WWW Yahoo
Search Engine Internet URL
1993 Internet Web Mosaic Netscape Navigator Web 1994 Internet Lycos Web Yahoo Internet Internet
Internet
Search Engine Internet URL
Web knowbot robot web crawler spider infobot
Web knowbot robot web crawler spider infobot
Internet and or not
stop word computer Internet a the what
1 car classic car
football game football game football game
basketball" basket weaving basket basketball
"space shuttle" outer space various spaces closer to home space shuttle
program
2 bed and breakfasts inns in Northern California bed and breakfasts inns "small hotels" in Northern California.
3
4
Robot Directory Catalog Meta
1 Robot Robot Spider Web Crawler Web Wanderer Web Robot Internet Robot " " Robot
Robot Robot Index URLs URLs "What s New" Usenet URLs URLs URLs Robot Robot URLs Web
Robot C Perl Java Unix Solaris Windows NT OS2 MAC Robot Web Robot Robot Robot
Index Robot Index HTML HTML HTML META
Robot Index Robot
Index Index
Excite
Index
2 Robot Web URL
Robot
Yahoo Internet 1998 Open Directory Internet Open Directory 14000
Robot Yahoo Robot
3 Meta Meta Multiple Search Engine
Meta Meta 10 50 Internet Meta
Meta Meta
Internet
1 Robot Robot
Yahoo Inktomi Yahoo http://search.yahoo.com/ http://ink.yahoo.com/
Yeah Infoseek Robot
2 Yahoo Email
Yahoo "My Yahoo " Infoseek "Personalized start page" Lycos "My Lycos"
3 AND OR NOT AltaVista Northern Light Lycos AltaVista NEAR
URL AltaVista Northern Light Infoseek
Internet
Internet 2000 Internet 10 Northern Light AltaVista 1 6 1 5 Internet Yahoo 120
1 Robot Robot
2 Robot Internet
Inktomi 100 SUN
Inktomi Internet Yahoo HotBot MSN Search AOL NetFind GoTo Inktomi
3 MP3
Web Mining
Internet InformationOverload Yahoo Robot
Robot WWW Robot
WebMining
Robot
1 2
3 4
5 Robot Web 6
1 (VSM VectorSpaceModal)
HTML HTML
2 " " " " " "
3 Robot HTTP Web HTML WWW Robot Spider Worm Crawler
Robot Web
4 NaiveBayes D P(Ci D) Ci argmaxp(ci D) P(Ci D) D Ci
WWW
--
" " (Meta- SearchEngine)
?
? ( )
411
( )
" " "
All-in-One
1 Metacrawler Savvysearch Profusion
2 All-in-one All-in-One ( )
All-in-one (WWW.albany.net allinone.himl) Allin-one
3
( ) EchoSearch WebCompass
1 checkbox Help 8-10 Lycos HotBot Alta Vista Excite
SavvySearch ProFusion 9 "best 3" "fastest 3" Dogpile 3 3
cookies SavvySearch SavvySearch 100 5-10
2 Web Usenet newswires DejaNews
3 "
( ) "Submit" Beaucoup Search Engines 14
4 " " 10 15 30??
5 1999 Cyber411
10 on Excite 1 on HotBot
InferenceFind VerioMetasearch 8 10
URL
6
1 Internet
2 Internet
3
4
5
6
3 B 166.111.0.0 166.111.255.255 65536 IP 65536 3 =1996608 =54.61 B
: 3 :
1 Internet
Internet Intranet Internet Internet
HTML HyperText Markup Language SGML Standard for General Markup Language XML extended Marked Language Word WPS
2
3
1
" " " " " " " " 3
2 " " " " " " " " " " " " " " "
3 " "
4 Word SVD Singular Value Decomposition
http://www.goyoyo.com.cn/main/indexgb.htm( ) http://www.goyoyo.sh.cn/( ) http://www.goyoyo.cq.cn/( ) http://www.goyoyo.com.hk/( ) http://www.goyoyo.com/( )
" " GOYOYO Robot " " 40 5
http://compass.net.edu.cn:8010 CERNet ChinaNet CSTNet ChinaGBN WWW 20
http://www.cseek.com CSEEK,, (GB) (BIG-5), Cseek,
YEAH http://www.yeah.net YEAH 4000
http://pccms.pku.edu.cn:8000/gbindex.htm WWW, CERNet" ",
WWW Web ( Web ) Newsgroup 60.6 WWW 9.6 Newsgroup URL
CEI http://infonavi.cei.gov.cn CEI CEI " " CEInet
http://www.robot.com.cn CNNIC,, " "
http://www.beijixing.com.cn AITECH Internet
http://www.sohoo.com.cn/ " "
" "
http://www.5415.com/ " " 10
http://gbchinese.yahoo.com/ Yahoo! Internet Interent
Yahoo! Yahoo!
http://www.omron.online.sh.cn/ SEARCH '97 Verity SEARCH'97 " " "
http://www.tonghua.com.cn/ "
http://www.yippee.com.cn/ Yippee WWW Yippee Yippee " "
http://www.whatsite.com.tw/ " " " " " " 40 " " GIF
http://www.yam.com.tw/ " "
COO http://www.coo.com.tw/ COO " " COO
http://www.hksrch.com/ 400 9000
http://www.c3s.org.sg/ AND OR, ((AAAANDBBB)OR(CCCORDDD))AND EEE OR
AltaVista http://altavista.digital.com/av/oneweb/query_ euccn.html AltaVista " " DEC AltaVista 27 Web 450 1.4 300 290
AltaVista
http://www.searchchina.com/ EIN EIN
(http://www.chinaok.com) (http://www.richsurf.com) (http://netcity.fz.fj.cn/guidenew/default.htm) (http://webpro.com.cn/search.htm) (http://www.online.xa.sn.cn/new/net/daohang/inde x.htm)
: (http://netcity.fz.fj.cn/guidenew/searchengin/sea rchengin1.htm) (http://www.east.cn.net/search) (http://www.rol.cn.net/station) (http://www.chinavigator.com.cn) (http://www.chineseresources.com) (http://www.homeway.com.cn)
(http://tnet.beijing.cn.net/gis/collection/int ernet/link_main.htm) (http://www.szptt.net.cn/info7.html) (http://newsnet.szptt.net.cn) (http://www.chinainfo.gov.cn) Netscape (http://www.netcenter.com/zh/cn/index.ht ml)
Verity TopicSearch " " " " and or not in
Yahoo
1994 4 Stanford David Filo Jerry Yang Internet Yahoo Yahoo Internet Internet
1995 Netscape Marc Andreessen Yahoo Filo Yang Netscape WWW Yahoo Yahoo Yet Another Hierarchical Oracle
Yahoo Yahoo WWW Internet WWW
Yahoo (http://www.yahoo.com)
WWW http://www.yahoo.com Yahoo Yahoo
Web FTP Web Yahoo
Yahoo Search Yahoo Yahoo Yahoo Yahoo
Yahoo Alta Vista Open Text Infoseek WebCrawler Lycos Yahoo
Yahoo Yahoo Alta Vista Web Yahoo
1. Option 2. Yahoo
+ t u URL
DOS * Yahoo Yahoo
Yahoo
Recreation and Sports Netscape Recreation and Sports Yahoo
1 2
Sports
Sports
football (american( american)
Yahoo Search +football +american+ american
Search
football american Search option option 1 7 Match on all words(and)
Alta Vista (http://www.altavista.com) DEC (Digital Equipment Corporation) Alta Vista Internet 2200 Web 110 13000 1995 12 DEC Palo Alto 800, 1-8
1-8
AltaVista Submit AltaVista searches SimpleSearch Advanced Search 1-9
1-9
Refine Refine Refine 1-10
1-10
Webcrawler (http://www.webcrawler.com Internet WWW 1994 University of Washington 1995 America Online 25 160 300 Webcrawler 25 WWW 1-12
1-12
WebCrawler natural language searching
AND gardening AND vegetables gardening vegetables OR whales OR cetaceans whales cetaceans NOT science NOT fiction science fiction NEAR arthritis NEAR/25 nutrition 25 NEAR
ADJ bal ADJ warming global warming "..." "1996 World Series Champions" (...) Homer NOT (Simpson OR Alaska) "1996 World Series Champions" 1996 ADJ World Series Champions Homer Homer Simpson Homer Alaska
WebCrawler Web URLs WebCrawler Shortcuts 1-13
Shortcuts 1-13
search WebCrawler Web Shortcuts hotels in San Francisco Guide to the Results Page
1 2 3 4 5 6 Shortcuts
Lycos(http://www.lycos.com) Carniege-Mellon Internet 1996 1 Lycos 1100 URL 91% Web WWW FTP Gopher
CentiSpeed 4000 Lycos Internet Lycos Search for football american Search Web sound picture personal homepages 5 (TOP5%) 1-14
1-14
Lycos Before, Far Lycos Help
InfoSeek(http://www.infoseek.com) 100 $9.95 Internet World 1996 5
InfoSeek Lycos Open Text Web InfoSeek Internet Computer Select 1-17
1-17
Open Text (http://www.opentext.com) Internet 100 Web Open Text (1) Open Text OR AND 1-18
1-18
(2) Search football american Any of these Words Search 1-19
1-19
Open Text football american Open Text Power Search back Open Text Index Power Search 1-20
1-20
Open Text Open Text Index- Power Search Search for football, And Followed By
Search for american Search Open Text football american 1-21
1-21 Open Text
World Wide Web Worm (http://www.cs.colorado.edu/home /mcbryan/wwww.html) WWW 1-22
1-22
Excite (http://www.excite.com) Internet WWW Architext Software Web Usenet 1-23
1-23
HotBot (http://www.hotbot.com) HotWire Web Hotwire Ventures Internet Alta Vista 1-24
1-24
Internet 98%
" " " "
ChinaRen
ChinaRen " " 8 28
CTO
Google " Google ogle "
" "
ChinaRen ChinaRen ChinaRen " "
ChinaRen CTO ChinaRen ChinaRen
Google 8 Google Google 163.com 15 Google 163.com
1998 Google 10 2400
CTO 20
OpenFind, OpenFind
CacheFlow JAVA SOQ
7 15 " ' ' ' ' " " " JAVA
CTO " 30 WWW 10
"
ChinaRen CTO ChinaRen ChinaRen CNNIC 10
5000