I am deeply indebted to Dr. Michael Berry, my major advisor, for his kind guidance and support. I also thank Dr. Susan Dumais, director of the Information Sciences Research Group at Bellcore, for her technical advice. In addition, she graciously allowed us
1.2TheFutureofInformationTechnology
Withtheamountofinformationavailableincreasingeachyearandthefactthatagreatdealoftheinformationexistsinelectronicformatsomepoint(whetheritispublishedelectronicallyormerelycreatedwithawordprocessor),informationretrievaltechniquesappearpoisedtobecomeincreasinglyvaluabletocasualusers,scientists,andbusinesses.Sinceinformationthatisinaccessibleisasmuchaproblemasthelackofinformation,searchingtechniquesthatcanautomaticallyderiveconceptualdatafromadocumentandallowausertosearchthatconceptualdatawillbecomemoreandmorepopularamongthosewhorequirelargeamountsofinformationtobeindexedand,perhaps,cross-indexedwithseeminglyunrelatedinformation.Thefollowingsectionsdescribethreeinterestingapplicationsofinformationtechnology:datamining,digitallibraries,andinformation ltering.
1.2.1DataMining
“Datamining”isafairlynewphraseusedtodescribetheprocessofautomati-callydiscoveringpatternsandderivingmeaningfromlargedatasets.Thechemi-cal/pharmaceutical,bankingand nancial,andretailingandmanufacturingindus-trieshavebuiltlargedatabasesofinformationrelatedtotheirday-to-daybusinessoperations.Theywanttousethedatatheyhavecollectedtopredictfuturebusi-nesstrends,developnewproducts,anddeterminetheeffectsofexternalfactors(forexample,advertising)ontheircurrentproductsandservices.Inparticular,thechem-ical/pharmaceuticalindustryoftenmustdeterminethelegal,social,http://www.77cn.com.cningdatamining,theindustryhopestostreamlinethesearchfornewchemicalsandmedicines,decreasingthetimeandcostofdevelopingnewproducts[DF95].
Althoughmanyattemptsatdatamininghavefocussedofneuralnetworksandmachinelearning,conceptualandvector-spacemodelsforinformationretrievalmaybeusefulforrepresentingthevastquantitiesofinformationgeneratedbytheseindustries,
3