2.2 Big data

Big data aka halitta da kuma tattara da gwamnatoci ga dalilai wanin bincike. Amfani da wannan labari domin gudanar da bincike, sabili da haka, na bukatar repurposing.

An idealized view of social bincike shayi masanin kimiyya da ciwon wani ra'ayin, sa'an nan kuma tattara bayanai domin Ya jarraba cewa ra'ayin. Wannan style of bincike take kaiwa zuwa wani m Fit tsakanin bincike tambaya da kuma data, amma yana da iyaka, domin mutum bincike sau da yawa ba su da albarkatun da ake bukata don tattara bayanan da suke bukata, kamar manyan, m, kuma na al'umma-wakilin data. Saboda haka, da yawa na zamantakewa da bincike a baya ya yi amfani da manyan-sikelin zamantakewa safiyo, kamar Gaba Social Survey (GSS), da {asar Amirka, National Zaben Nazarin (ANES), da kuma Panel Nazarin Income ƙarfafa (PSID). Wadannan manyan-sikelin binciken da ake kullum gudu da wata tawagar masu bincike kuma suna tsara don ƙirƙirar data cewa za a iya amfani da mutane da yawa masu bincike. Domin daga cikin raga na wadannan manyan-sikelin safiyo, mai girma kulawa ne ya sa a cikin zayyana data tarin da kuma shirya sakamakon data don amfani da masu bincike. Wadannan bayanai da bincike da kuma masu bincike.

Mai zamantakewa bincike ta amfani da digital shekaru kafofin, duk da haka, shi ne fundamentally daban-daban. Maimakon yin amfani da bayanai da aka tattara daga masu bincike da kuma masu bincike, yana amfani da data kafofin da aka halitta da kuma tattara da harkokin kasuwanci da kuma gwamnatocin ga nasu dalilai kamar yin riba, samar da wani sabis, ko bayar da wata doka. Wadannan kasuwanci da kuma gwamnatin data kafofin sun zo a kira babban data. Yin bincike tare da babban data ne daban-daban fiye da yin bincike da bayanai da aka asali halitta bincike. Kwatanta, misali, a kafofin watsa labarun website, kamar Twitter, da gargajiya da jama'a ra'ayi binciken kamar Gaba Social Survey (GSS). Twitter babban raga ne don samar da wani sabis ta zuwa ga masu amfani da kuma yin riba. A cikin aiwatar da wadannan cimma burin, Twitter halitta data da zai zama da amfani ga nazarin wani al'amurran da jama'a ra'ayi. Amma, sabanin Gaba Social Survey (GSS), Twitter ba da farko mayar da hankali a kan zamantakewa da bincike.

Kalmar babban data ne frustratingly m, kuma shi kungiyoyin game da yawa daban-daban abubuwa. Ga dalilai na zamantakewa da bincike, ina ganin yana da m rarrabe tsakanin iri biyu babba data kafofin: gwamnatin administrative records da kuma kasuwanci administrative records. Gwamnatin administrative records ne data da aka halitta da gwamnatoci a matsayin wani ɓangare na su na yau da kullum da ayyukan. Wadannan iri records da aka yi amfani da masu bincike a baya-kamar demographers nazarin haihuwa, aure, da mutuwa records-amma gwamnatoci suna ƙara tattara da kuma sakewa cikakken records a analyzable siffofin. Alal misali, New York City gwamnatin shigar digital mita cikin kowane taxi a cikin birnin. Wadannan mita rikodin duk iri bayanai game da kowace taxi tafiya ciki har da direba, da farko lokaci da wuri, da tasha lokaci da wuri, da kuma kudin tafiya. A wani binciken da zan gaya daga baya a wannan babi, Henry Farber (2015) repurposed wadannan data ga magance wata muhimman hakkokin muhawara a aiki tattalin arziki game da dangantaka tsakanin hourly Hakkin kuma yawan hours aiki.

Na biyu main irin babban data for zamantakewa bincike ne business administrative records. Waɗannan su ne data cewa business halitta da kuma tattara a matsayin wani ɓangare na su na yau da kullum da ayyukan. Wadannan aiki administrative records sukan kira digital burbushi, kuma sun hada da abubuwa kamar search engine query rajistan ayyukan, kafofin watsa labarun posts, da kuma kira records daga mobile phones. Kafofin yada, wadannan business administrative records ne ba kawai game da online hali. Alal misali, Stores cewa amfani duba-fitar Scanners samar real-lokaci da matakan ma'aikacin yawan aiki. A wani binciken da zan gaya muku game da daga baya a wannan babi, Alexandre Mas da Enrico Moretti (2009) repurposed wannan babban kanti duba-fito data yi nazarin yadda za a ma'aikata 'aiki ne tasiri da yawan aiki na da takwarorinsu.

As biyu daga cikin wadannan misalai nuna, da ra'ayin repurposing ne na asali ga koyo daga babban data. A na kwarewa, zamantakewa masana kimiyya da kuma bayanan masana kimiyyar kusanci wannan repurposing sosai daban. Social masana kimiyya, da suka saba wa aiki da data tsara don gudanar da bincike, su ne m don nuna da matsaloli tare da repurposed data yayin kyalewa da karfi. A daya hannun, data masana kimiyya ne m nuna amfanin repurposed data yayin kyalewa da kasawan. Ta halitta, mafi kyau m zai zama matasan. Wancan ne, masu bincike bukatar fahimtar halaye na wadannan sababbin kafofin data-biyu mai kyau da kuma mummuna-sa'an nan kuma Figure fitar da yadda za a koya daga gare su. Kuma, shi ne shirin da saura na wannan babi. Next, zan bayyana goma kowa halaye na kasuwanci da kuma gwamnatin administrative data. Bayan haka, zan bayyana uku bincike fuskanci cewa za a iya amfani da wadannan bayanai, ta kusance cewa suna da kyau dace da halaye na wannan bayanai.