Jia Sun Ben Shneiderman Ping Wang amp Yan Qu cdunne bencsumdedu pengyi chhuang jsun pwang yanqu umdedu http stickischoolumdedu 28 th Annual HumanComputer Interaction Lab Symposium ID: 782664
Download The PPT/PDF document "Cody Dunne, Pengyi Zhang, Chen Huang," is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Cody Dunne, Pengyi Zhang, Chen Huang, Jia Sun,Ben Shneiderman, Ping Wang & Yan Qu{cdunne, ben}@cs.umd.edu{pengyi, chhuang, jsun, pwang, yanqu}@umd.eduhttp://stick.ischool.umd.edu28th Annual Human-Computer Interaction Lab SymposiumMay 25-26, 2011 College Park, MD
Analyzing Trends in Science & Technology Innovation
Slide2Business Intelligence 2000-20092006 Peak: Concept-Entity Co-OccurrenceYearFrequencyData MiningNational Security AgencyNSAWhite HouseFBIAT&TAmerican Civil Liberties UnionElectronic Frontier FoundationDept. of Homeland SecurityCIA
Slide3Business Intelligence 2000-20092006 Peak: Entity Co-OccurrenceYearFrequencyNSANatl. Security AgencyNSAWhite HouseAT&TNatl. Security AgencyNSAAT&TNSAFBINSAEFFNSAACLU
NSACIA
AT&T
EFF
NSA
Pentagon
Pentagon
White House
AT&T
White House
ACLU
White House
Slide4Business Intelligence2000-2009Matrix showing Co-Occurrence of concepts and entities
Slide5Business Intelligence2000-2009:(subset)
Slide6Business Intelligence2000-2009:Data miningNSACIAFBIWhite HousePentagonDODDHSAT&TACLUEFFSenate Judiciary Committee
Slide7Business Intelligence2000-2009:Tech1 GoogleYahooStanfordAppleTech2IBM, CognosMicrosoftOracleFinanceNASDAQNYSESECNCRMicroStrategy
Slide8Business Intelligence2000-2009:Air ForceArmyNavyGSAUMD*
Slide9Business Intelligence2000-2009Network showing Co-Occurrence of concepts and entities
Slide10Business Intelligence2000-2009Co-Occurrence of concepts and entities(subset)
Slide11The STICK ProjectNSF SciSIP ProgramScience of Science & Innovation PolicyGoal: Scientific approach to science policyThe STICK ProjectScience & Technology Innovation Concept Knowledge-baseGoal: Monitoring, Understanding, and Advancing the (R)Evolution of Science & Technology Innovations
Slide12STICK ContributionScientific, data-driven way to track innovationsVs. current expert-based, time consuming approaches (e.g., Gartner’s Hype Cycle, tire track diagrams)Includes both concept and product formsStudy relationships betweenStudy the innovation ecosystemOrganizations & peopleBoth those producing & using innovations
Slide13ProcessCollectingProcessingVisualizing & AnalyzingCollaboratingCleaning
Slide14CollectingIdentify ConceptsBegin with target conceptsBusiness IntelligenceHealth ITCloud ComputingCustomer Relationship ManagementWeb 2.0Develop 20-30 sub concepts from domain experts, wikisData SourcesNews DissertationAcademicPatentBlogs
Slide15Collecting (2)Form & Expand QueriesABS("customer relationship management" OR"customers relationship management" OR"customer relation management") OR TEXT(…) OR SUB(…) OR TI(…)Scrape Results
Source: http://
xkcd.com/208
Slide16ProcessingAutomatic Entity RecognitionBBN IdentiFinderCrowd-Sourced VerificationExtract most frequent 25%Assign to CrowdFlowerWorkers check organization names and sample sentences
Slide17Processing (2)Compute Co-Occurrence NetworksOverall edge weightsSlice by time to see network evolutionOutputCSVGraphML
Slide18Visualizing & AnalyzingSpotfireImport CSV, DatabaseStandard chartsMultiple coordinated viewsHighly scalableNodeXLCSV, Spigots, GraphMLAutomate featureBatch analysis & visualizationExcel 2007/2010 template
Slide19CollaboratingOnline Research CommunityShare data, tools, resultsData & analysis downloadsSpotfire Web PlayerCommunicationCo-creation, co-authoring
Slide20Ongoing WorkCollecting:Additional data sources and queriesProcessing:Improving entity recognition accuracyVisualizing & Analyzing:Visualizing network evolutionCo-occurrence network sliced by timeCollaborating:Develop the STICK Community siteMotivate user participationImprove the resources availableLocal testingInvitation-only testing
Slide21Take Away MessagesEasier scientific, data-driven innovation analysis:Automatic collection & processing of innovation dataEasy access to visual analytic tools for finding clusters, trends, outliersCommunities for sharing data, tools, & results
Slide22Cody Dunne, Pengyi Zhang, Chen Huang, Jia Sun,Ben Shneiderman, Ping Wang & Yan Qu{cdunne, ben}@cs.umd.edu{pengyi, chhuang, jsun, pwang, yanqu}@umd.eduhttp://stick.ischool.umd.eduThanks to: National Science Foundation grant SBE-0915645
Analyzing Trends in Science & Technology Innovation