Soj ntsuam scraped me nyuam kawm ntawv cov ntaub ntawv los ntawm Facebook, merged nrog tsev kawm ntawv cov ntaub ntawv, siv no merged cov ntaub ntawv rau kev tshawb fawb, thiab ces muab qhia nrog lwm cov neeg tshawb fawb.
Pib nyob rau hauv 2006, txhua xyoo ib pab neeg ntawm cov professors thiab kev tshawb fawb pab scraped lub Facebook profiles ntawm tag nrho cov mej zeej ntawm lub chav kawm ntawv xyoo 2009 thaum ib tug "ntau haiv neeg ntiag tug kawm ntawv qib siab nyob rau hauv lub Northeastern US" Qhov no longitudinal ntaub ntawv los ntawm Facebook rau kev phooj ywg thiab keeb kwm kev cai tastes twb merged nrog cov ntaub ntawv cov kawm ntawv qib muaj txog cov menyuam kawm ntawv thaj dorms thiab kev kawm majors. Qhov no merged cov ntaub ntawv sawv cev ib tug tseem ceeb pab rau kev soj ntsuam, thiab nws tau siv los tsim kev paub tshiab txog tej yam xws li yuav ua li cas kev tes hauj lwm daim ntawv (Wimmer and Lewis 2010) thiab yuav ua li cas kev tes hauj lwm thiab kev coj cwj pwm co-evolve (Lewis, Gonzalez, and Kaufman 2012) . Nyob rau hauv tas li ntawd mus siv cov ntaub ntawv rau lawv tus kheej ua hauj lwm, lub saj, Ties, thiab lub sij hawm pab neeg tshawb fawb ua cov ntaub ntawv muaj rau lwm yam kev soj ntsuam, tom qab noj ib co kauj ruam los tiv thaiv cov menyuam kawm ntawv 'ceev kev ntiag tug thiab nyob rau hauv txoj kab nrog rau xav li cas ntawm lub National Science Foundation ( uas pab nyiaj rau txoj kev tshawb) (Lewis et al. 2008) .
Tu siab, cia li hnub tom qab cov ntaub ntawv twb tau muaj, lwm yam kev soj ntsuam deduced hais tias lub tsev kawm ntawv nyob rau hauv lo lus nug yog Harvard College (Zimmer 2010) . Lub saj, Ties, thiab lub sij hawm soj ntsuam raug liam hais tias ntawm ib tug "tsis ua hauj lwm ua raws li raug cai tshawb fawb kev cai" (Zimmer 2010) nyob rau hauv ib feem vim hais tias cov me nyuam kawm ntawv tsis tau muab qhov kev tso cai (tag nrho cov txheej txheem saib thiab pom zoo los ntawm Harvard lub IRB thiab Facebook). Nyob rau hauv tas li ntawd mus thuam los ntawm kev kawm ntawv, cov ntawv xov xwm cov khoom tshwm sim tuaj nrog headlines xws li "Harvard Soj ntsuam liam ntawm breaching Cov menyuam kawm ntawv 'Tsis pub twg paub" (Parry 2011) . Thaum kawg, lub dataset raug tshem tawm los ntawm lub Internet, thiab tam sim no nws yuav siv tsis tau los ntawm lwm yam kev soj ntsuam.