Content Analysis with Stata

1 Content Analysis with StataM. Alonso de Salamanca8th Spanish Stata Users Group meetingMadrid, 22thOctober-2015 Modesto Escobar & A. Berrocal (USAL) Content Analysis22th October 20151 / 54 Table of ContentsOverviewBackgroundContent analysisSocial network analysisCoincidence analysisStata users-written commandsThe command precoinMultiple variablesThesaurus stringsWordsThe command coinNext stepsModesto Escobar & A. Berrocal (USAL) Content Analysis22th October 20152 / 54 BackgroundContent AnalysisContent AnalysisDefinitionsContent Analysis is a technique used in the social sciences for thesystematic study of the contents of the communication. A systematic, replicable technique for compressing many words oftext into fewer Content categories based on explicit rules of coding [Berelson, 1952]. Any technique for making inferences by objectively andsystematically identifying specified characteristics of messages [Holsti, 1969]. Content Analysis is a research technique for making replicable andvalid inferences from data to their context [Krippendorff, 1980].

2 Modesto Escobar & A. Berrocal (USAL) Content Analysis22th October 20153 / 54 BackgroundPrograms for Content analysisSoftware for Content analysisProgramsQualitative analyzersNvivoAtlas-tiQDA minerStatistical analyzersWordStatTextAnalystLIWCM odesto Escobar & A. Berrocal (USAL) Content Analysis22th October 20154 / 54 BackgroundQualitative Analysis programsQualitative Analysis programsNvivoModesto Escobar & A. Berrocal (USAL) Content Analysis22th October 20155 / 54 BackgroundQualitative Analysis programsQualitative Analysis programsAtlas-tiModesto Escobar & A. Berrocal (USAL) Content Analysis22th October 20156 / 54 BackgroundStatistical analyzersStatistical analystsWordStat for QDA (and for Stata )Modesto Escobar & A. Berrocal (USAL) Content Analysis22th October 20157 / 54 BackgroundSocial network analysisSocial network analysisStata programsAlthough there are no tools for SNA in Stata , some advanced usershave begun to write some routines. I wish to highlight the followingworks from which I have obtained insights:Corten [2011] wrote a routine to visualize social networks [netplot]Miura [2012] created routines (SGL) to calculate networks centralitymeasures, including two Stata commands [netsis and netsummarize]White presented a suite of Stata programs for network meta-analysiswhich includes the network graphs of Anna Chaimani in the 2013 UKusers group meeting.

3 Cerulli and Zinilii presented a procedure [datanet]to prepare a dataset for Analysis purposes in the 2014 Italian StataUsers Group [2014] have created a collection of programs to plot and analyzesocial networks in the Nordic and Baltic Stata Users Group[nwcommands].Modesto Escobar & A. Berrocal (USAL) Content Analysis22th October 20158 / 54 BackgroundCoincidence analysisCoincidence analysisDefinitionCoincidence Analysis is a set of techniques whose object is to detect whichpeople, subjects, objects, attributes or events tend to appear at the sametime in different delimited delimited spaces are called scenarios (n), and are considered asunits of Analysis (i).In each scenario a number ofJeventsXjmay occur (1) or may not(0) starting point is an incidence matrix (X) ann Jmatrixcomposed by 0 and 1, according to the incidence or not of Escobar & A. Berrocal (USAL) Content Analysis22th October 20159 / 54 BackgroundOld examplePictures analysis4 pictures (scenarios) & 8 different people (events)Modesto Escobar & A.

4 Berrocal (USAL) Content Analysis22th October 201510 / 54 BackgroundAlbums AnalysisExample with namesFather, mother, grandmother and 5 childrenModesto Escobar & A. Berrocal (USAL) Content Analysis22th October 201511 / 54 BackgroundAlbums AnalysisExample with codesTurina, Garz on, Joaqu n, Mar a, Concha, Jos e Luis, Obdulia, ValleModesto Escobar & A. Berrocal (USAL) Content Analysis22th October 201512 / 54 BackgroundAlbums AnalysisCoincidences graphsMDS-Biplot-CA-PCAJ oaqu n TurinaObdulia Garz nJoaqu nMar aConchaJos LuisObduliaJosefa ValleJosefa Garz nMDS coordinatesTurina (MDS)Joaqu n TurinaObdulia Garz nJoaqu nMar aConchaJos LuisObduliaJosefa ValleJosefa Garz nBIPLOT coordinatesTurina (Biplot)Joaqu n TurinaObdulia Garz nJoaqu nMar aConchaJos LuisObduliaJosefa ValleJosefa Garz nCA coordinatesTurina (CA)Joaqu n TurinaObdulia Garz nJoaqu nMar aConchaJos LuisObduliaJosefa ValleJosefa Garz nPCA coordinatesTurina (PCA)Modesto Escobar & A. Berrocal (USAL) Content Analysis22th October 201513 / 54 BackgroundOther analysisOther uses of coincidence analysisFrom survey Analysis to cultural trendsCoincidence Analysis has many applications.

5 Among others:Survey analysisUnemploymentSocial problemsMass media audienceData MiningSamples (Composition of genes)Corruption (Black cards)Cultural trendsComposersPaintersCreatorsContent analysisModesto Escobar & A. Berrocal (USAL) Content Analysis22th October 201514 / 54 BackgroundSurvey analysisSurvey analysisWays of looking for jobs (EPA-2014)Age: youngAge: adultAge: olderAgency: publicAgency: privateContacts: employersContacts: informalAds: placingAds: looking atSelf: employmentSelf: loanWaiting: offersWaiting: resultsOthers: interviewsOthers: examsOthers: othersAgencies/SearchContacts/ coordinatesModesto Escobar & A. Berrocal (USAL) Content Analysis22th October 201515 / 54 BackgroundSurvey analysisSurvey analysisSocial problems in Spain (2014) CIS-3045El paroLa sanidadProblemas econ micosLa corrupci n y el fraudeLos/as pol ticos/as en generalLos problemas de ndole socialLa educaci nOtras respuestasP26==HombreP26==MujerEdad==Jov enEdad==AdultoEdad==MayorESTUDIOS==Sin estudiosESTUDIOS==PrimariaESTUDIOS==Secu ndaria 2 etapaESTUDIOS== mico/ProblemaSocial/ProblemaPol ticos/ProblemaOtros/ProblemaG nero/G neroEdad/EdadEstudios/EstudiosMDS coordinatesESTUDIOS==Secundaria 1 etapaEdad==MaduroModesto Escobar & A.

6 Berrocal (USAL) Content Analysis22th October 201516 / 54 BackgroundSurvey analysisSurvey analysisMass media audience (EGM-2013)NO newspaperMARCAEL PA S20 MINUTOSEL MUNDOLA VANGUARDIAASEL PERI DICOEL MUNDO DEPORTIVOSPORTABCLA VOZ DE GALICIALA RAZ NEXPANSI NANTENA3 TELECINCOTVE1LA SEXTACUATRONO channelTV3 TVE2 NOVACANAL SURFACTORIA DE FICCION (FDF)XPLORANEOXDISCOVERY MAXLA SEXTA3 NITRODIVINITY24 HORAS TVENO cadenaSERC40 INDPEOCRCDIALCOPEEUROPAC100 RNE1 RAC1 CAT_RAKISSFMNO magazineHOLAPRONTOLECTURASDIEZ MINUTOSSEMANAMUY INTERESANTENATIONAL GEOGRAPHICINTERVIUSABER VIVIREL JUEVESCUOREOTRAS REVISTASVOGUEQUOHISTORIA NATIONAL GEOGRAPHICM AEL MUEBLEQUE ME DICESELLECOSMOPOLITANMICASACOCINA F CILCOSAS DE CASAMI BEBE Y YOPELO PICO PATACASA DIEZGLAMOURVIAJES NATIONALGEOGRAPHICRACC CLUBTELVATIEMPOMARCA MOTORFOTOGRAMASLABORES DEL HOGARJARA Y SEDALAUTOPISTACLARALECTURAS ESPECIAL COCINASER PADRESARSOLO MOTO ACTUALM odesto Escobar & A. Berrocal (USAL) Content Analysis22th October 201517 / 54 BackgroundData miningData miningGenes composition of samples.

7 Fuente: Omni GenotypesHas Axiom GenotypesHas Affy GenotypesHas Exome/LOF GenotypesACBASWBEBCDXCEUCHBCHSCLMESNFING BRGIHGWDIBSITUJPTKHVLWKMSLMXLPELPJLPURST UTSIYRIA frica/SampleAmerica/SampleAsia/SampleEur ope/SampleOmni/GenotypeAxiom/GenotypeAff y/GenotypeExome/GenotypeFruchterman-Rein gold coordinatesModesto Escobar & A. Berrocal (USAL) Content Analysis22th October 201518 / 54 BackgroundData miningData miningMean expenses per person with Bankia black cards (2003-2011)Restaurante normalGasto comprasCajeros autom ticosRestaurantes lujoGasolinerasHotelesCulturaJoyasFlores TaxisClubesMetroDerechaSocial-democracia IzquierdaModesto Escobar & A. Berrocal (USAL) Content Analysis22th October 201519 / 54 BackgroundCultural trendsCultural trendsBachtack concerts reviewed (2009-2015)BeethovenMozartBrahmsBachRave lTchaikovskySchubertShostakovichMahlerDe bussyStravinskySchumannBrittenDvorakHayd nStraussRRachmaninovProkofievWagnerBarto kMendelssohnHandelSibeliusBrucknerElgarL isztBerliozChopinVivaldiBarrocoCl sicoRom nticoSiglo XXMDS coordinatesModesto Escobar & A.

8 Berrocal (USAL) Content Analysis22th October 201520 / 54 BackgroundCultural trendsCultural trendsCreators in Juan March exhibitions (1975-2015)Z bel, FernandoSaura, AntonioMillares, ManuelT pies, AntoniSempere, EusebioGuerrero, Jos Feito, LuisRueda, GerardoRivera, ManuelTorner, GustavoMu oz, LucioHern ndez Momp , ManuelFarreras, FranciscoPicasso, PabloGuinovart, JosepChillida, EduardoCuixart, ModestPon , JoanPalazuelo, PabloMir , JoanChirino, Mart nHern ndez Pijuan, JoanGenov s, JuanGonz lez, JulioKandinsky, WassilyCanogar, RafaelL pez Hern ndez, JulioLaff n, CarmenRauschenberg, RobertGabino, AmadeoClav , AntonioL pez Garc a, AntonioLorenzo, AntonioLichtenstein, RoyViola, ManuelBerrocal, MiguelFranc s, JuanaEquipo Cr nica,Victoria, SalvadorWarhol, AndyKlee, PaulSchwitters, KurtBalaguer , Jos LuisKokoschka, OskarVilacasas, JoanBraque, GeorgesClav , AntoniBrinkmann, EnriqueBurguillos, JaimeNolde, EmilTharrats, Joan JosepPuig, AugustVaquero Turcios, Joaqu nSoria, SalvadorClaret, JoanGran, EnriqueBeckmann, MaxErnst, MaxAlbers, JosefMoholy-Nagy, L szl L ger, FernandLudwig Kirchner, ErnstRedon, Odilonde Goya.

9 FranciscoR dchenko, Alexandrde Toulouse-Lautrec, HenriVasarely, VictorStella, FrankCalder, AlexanderGordillo, LuisJohns, JasperBill, Maxde Kooning, WillemKlimt, GustavMalevich, KasimirMonet, ClaudeGarc a-Alix, AlbertoDegas, EdgarChagall, MarcArp, JeanLissitzky, ElLeWitt, SolHeckel, ErichMotherwell, RobertBayer, HerbertRodin, AugusteRothko, MarkBrossa, JoanPopova, LiubovDelaunay, RobertMapplethorpe, RobertMunch, EdvardGiacometti, AlbertoSherman, CindySchiele, EgonMatisse, HenriBonnard, PierreAndre, CarlKosuth, JosephMolzahn, JohannesMorris, RobertBaumeister, WilliSchlemmer, OskarDix, OttoPollock, JacksonDavid Friedrich, CasparHaussmann, RaoulCruz-D ez, CarlosOpalka, RomanPenn, IrvingJ. Schoonhoven, JanGrosz, Georgeentre otros,Lutschischkin, SergeiDal , SalvadorErmilov, VassilyLehmbruck, WilhelmKul guina, ValentinaNauman, BruceJudd, DonaldOldenburg, ClaesMadoz, ChemaTinguely, JeanDubuffet, JeanBacon, FrancisTeixidor, JordiNoland, KennethSchmidt-Rottluff, KarlRuff, ThomasPrusakov, NikolaiFontana, LucioBuren, DanielCartier-Bresson, HenriGottlieb, AdolphMack, HeinzManzoni, PieroSoto, Jes s RaphaelC zanne, PaulMondrian, PietMueller, OttoDarboven, HanneSenkin, SergeiManet, douardSchuitema, PaulCassandre, AdolpheScully, SeanKlucis, GustavsBoltanski, ChristianRuscha, EdwardRyman, RobertBissier, JuliusHockney, DavidBaselitz, GeorgRazulevich, Mija lAltman, NatanR hl, Karl PeterRosenquist, JamesSerrano, PabloVerheyen, JefHeartfield, JohnFrancis, SamKelly, EllsworthGarc a Rodero, CristinaStenberg, Gue rguiSerra, RichardMoore, HenryTorres-Garc a, Joaqu nGauguin, PaulMorandi, GiorgioSutnar, LadislavMcKnight Kauffer, EdwardUecker, G nthervon Graevenitz, GerhardSenkin.

10 Sergu iR dchenko, AleksandrFlavin, DanWesselmann, Tomvon Jawlensky, AlexejKline, FranzDexel, WalterGursky, AndreasRohlfs, ChristianBroodthaers, MarcelArbus, DianeCapa Eiriz, Joaqu nStenberg, Vlad mirTobey, MarkTrump, GeorgLong, RichardDibbets, JanNewman, BarnettCarlu, JeanMagritte, Ren Miralda, Anton Lechuga, DavidMorellet, Fran oisVantongerloo, GeorgesSeurat, GeorgesSisley, AlfredZush, AlbertoTschichold, JanBordes, JuanZwart, PietNicholson, BenKlein, YvesMangold, RobertLohse, Richard PaulNo authorsModesto Escobar & A. Berrocal (USAL) Content Analysis22th October 201521 / 54 BackgroundCultural trendsCultural trendsTimeline of famous portrait paintersAlberto DureroAndy WarholChuck CloseDiego Rodr guez de Silva y VelDomenico GhirlandaioFerdinand HodlerFrancis BaconFrancisco Jos de Goya y LucieFran ois BoucherGiovanni Battista MoroniGiseppe ArcimboldoGustave CourbetHans Holbein el jovenHyacinthe RigaudJacques-Louis DavidJan Van EyckJean-Auguste-Dominique IngresJean-Honor FragonardJoshua ReynoldsLeonardo da VinciLucien FreudOskar KokoschkaPablo PicassoParmigianinoPedro Pablo RubensPiero della FrancescaRafaelRembrandt Harmenszoon van RijnThomas GainsboroughTizianoVincent Van GouhWilhem Leibl douard ManetMDS coordinatesModesto Escobar & A.