Treść książki
Przejdź do opcji czytnikaPrzejdź do nawigacjiPrzejdź do informacjiPrzejdź do stopki
bigdata,datamining,
digitalarchives,datavisualization
PiotrGAWRYSIAK
InstytutInformatyki
PolitechnikaWarszawska
HUMANITIESANDBIGDATA.
EXPLOITINGDIGITALARCHIVES
INTHEAGEOFABUNDANCE
Widespreaddigitizationeńortsundertakeninrecentyearsresultedincreationof
onlinerepositoriesofhumanitiessourcematerialsofunprecedentedscale.While
theinformationstoredinthesedigitalarchivesisimmediatelyusefulinasame
senseastheoriginalpublicationsthatweredigitized,itisalsomuchmoreame-
nabletoautomatedprocessinginthedigitalform.Meanwhile,thecurrentstate
oftheartinmachinelearninganddistributedprocessingtechnologycreated
asituation,inwhichadvanced,largescale(socalled“bigdata”)analysistoolsare
widelyavailableeventosmallresearchinstitutionswithmodestbudgets.Tese
twotrendsshould,asthispaperpostulates,beexploitedinordertogainnew
insightnotavailablepreviouslyinhumanities.
1.INTRODUCTION
Tankstorecentadvancementsindigitizationandstoragetechnology,the
humanitiesareclosetoanimportanttippingpointinthehistoryofthisfield
ofscience.Tepointwherealmostalltheartifactsthataresubjectofscientific
researchwillbeavailableinadigitalform,freefromtheconstraintsoftime
andspace–andthusavailabletoeveryoneontheglobe.Indeed,evennowthe
mostimportantcollectionsofvisualartsandliteraryandscientificwritingare
alreadydigitizedandreachableviatheInternet.Tequality,oreaseofuseor
accessconditionstothesecollectionsaresometimesnotentirelysatisfactory,
buttheyarequicklyimproving.Ageofabundanceinthehumanitiesisalready
