{"id":"W4392846024","doi":"10.1145/3625007.3627479","title":"Designing a Natural Language Processing System to Support Social Science Research","year":2023,"lang":"en","type":"article","venue":"","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Natural (archaeology)","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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0102833,0.00004852056,0.00009623687,0.0005503756,0.002708727,0.0003524163,0.0003784845,0.00002660094,0.00006506121],"category_scores_gemma":[0.0006484726,0.00004179033,0.00003998245,0.006615694,0.0003291742,0.0002298759,0.0001436889,0.000122872,0.0003296902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002205772,"about_ca_system_score_gemma":0.0007036543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006766699,"about_ca_topic_score_gemma":0.0002390401,"domain_scores_codex":[0.9974263,0.0003286835,0.0001254343,0.0002546896,0.001369112,0.0004957795],"domain_scores_gemma":[0.9990671,0.0002788384,0.00002418813,0.00005538068,0.0004505499,0.0001239029],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001209804,0.00001878455,0.0007679517,0.000046893,0.0000106497,0.00005123545,0.1779232,0.000061258,0.01323981,0.09346811,0.004648909,0.7097511],"study_design_scores_gemma":[0.0003579803,0.0001022154,0.02103692,0.0001190652,0.00002885313,0.000005135573,0.9106045,0.04231133,0.003731575,0.002379554,0.01864744,0.0006754647],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.4257834,0.00007538414,0.01529908,0.004592795,0.0004972661,0.0005218324,0.000001770773,0.001120373,0.5521081],"genre_scores_gemma":[0.9822331,2.810108e-7,0.00673931,0.00006506486,0.0003484995,0.00001447867,0.000001626615,0.000004828315,0.0105928],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7326813,"threshold_uncertainty_score":0.9985896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1739238738311632,"score_gpt":0.5421152357581502,"score_spread":0.368191361926987,"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."}}