{"id":"W4310576792","doi":"10.1177/00491241221123088","title":"From Ends to Means: The Promise of Computational Text Analysis for Theoretically Driven Sociological Research","year":2022,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Skepticism; Field (mathematics); Relevance (law); Management science; Set (abstract data type); Computational model; Epistemology; Selection (genetic algorithm); Computational sociology; Data science; Process (computing); Sociology; Artificial intelligence; Political science","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":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.09616744,0.0001766877,0.000715454,0.0006165434,0.004796056,0.0001142436,0.001994361,0.0002516362,0.004642138],"category_scores_gemma":[0.02166873,0.0001152811,0.0007760964,0.005022982,0.004946711,0.00005269825,0.001329954,0.001723004,0.00002307089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004313441,"about_ca_system_score_gemma":0.0006834728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009205526,"about_ca_topic_score_gemma":0.0000515748,"domain_scores_codex":[0.9332029,0.06137319,0.0006671379,0.0008738088,0.002848344,0.001034646],"domain_scores_gemma":[0.9047949,0.09248824,0.0001317736,0.0003849402,0.001896946,0.0003032136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004812182,0.0004857278,0.003958033,0.000008001253,0.001018059,0.000004815085,0.03666909,0.02182173,0.0009749343,0.860086,0.002007676,0.07248474],"study_design_scores_gemma":[0.000247517,0.0005179988,0.01307212,0.0000030618,0.0001115888,2.106438e-7,0.03173113,0.01215058,0.00003163528,0.9228437,0.01913661,0.0001538423],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2435351,0.0005064528,0.6876985,0.05424897,0.0001922619,0.002563378,0.0002869354,0.00009804356,0.01087034],"genre_scores_gemma":[0.6546878,0.00001998512,0.3429888,0.0002439734,0.0004391833,0.0009805417,0.00007061293,0.00001138434,0.0005576586],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4111527,"threshold_uncertainty_score":0.9977612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4486729254285306,"score_gpt":0.6277772920025255,"score_spread":0.1791043665739949,"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."}}