{"id":"W2959359514","doi":"10.18146/2213-0969.2018.jethc151","title":"Maps, Distant Reading and the Internet Movie Database","year":2018,"lang":"en","type":"article","venue":"VIEW Journal of European Television History and Culture","topic":"Digital Humanities and Scholarship","field":"Arts and Humanities","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Big data; The Internet; Reading (process); Data science; Computer science; Analytics; Scale (ratio); World Wide Web; Order (exchange); Circulation (fluid dynamics); Raw data; Production (economics); Cultural analytics; Geography; Cartography; Political science; Engineering; Semantic analytics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007269342,0.000804222,0.0007059668,0.008973504,0.0007697304,0.003049104,0.001180261,0.0008051167,0.03508411],"category_scores_gemma":[0.00625004,0.0002929997,0.0006110683,0.01448999,0.0003820977,0.004413624,0.001859074,0.0009391131,0.03246064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006659288,"about_ca_system_score_gemma":0.001019503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02960449,"about_ca_topic_score_gemma":0.035453,"domain_scores_codex":[0.9991497,0.0001145471,0.00009669591,0.0001830556,0.0003790823,0.00007686167],"domain_scores_gemma":[0.9975632,0.0005463336,0.0002118217,0.0007678938,0.0005706404,0.0003400104],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005309723,0.0001382113,0.009083507,0.001367248,0.0001761965,0.0003175984,0.0006176425,0.002385312,0.0006272555,0.008620172,0.8539822,0.1221536],"study_design_scores_gemma":[0.00009534368,0.0000445005,0.02539777,0.0001846272,0.00006378384,0.0002691197,0.001140081,0.007742853,0.001497456,0.01138979,0.9520649,0.0001097048],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.01684849,0.002851913,0.006455794,0.001408302,0.0003088836,0.0001419873,0.8924116,0.03228114,0.04729179],"genre_scores_gemma":[0.05360641,0.002032497,0.01264371,0.000215778,0.0001891525,0.0001380936,0.9189959,0.001596358,0.01058212],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03508411,"threshold_uncertainty_score":0.117368,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03877087580245349,"score_gpt":0.2207803793817033,"score_spread":0.1820095035792498,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}