{"id":"W3215074405","doi":"10.1145/3492844","title":"The Computational Thematic Analysis Toolkit","year":2022,"lang":"en","type":"article","venue":"Proceedings of the ACM on Human-Computer Interaction","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Computer science; Transparency (behavior); Thematic analysis; Data science; Variety (cybernetics); Interface (matter); Coding (social sciences); Computational model; Thematic map; Modular design; Computational sociology; Process (computing); Human–computer interaction; World Wide Web; Qualitative research; Artificial intelligence; Sociology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.02817894,0.0020999,0.001642867,0.007563906,0.003409159,0.008543228,0.005618544,0.001712032,0.04851327],"category_scores_gemma":[0.06758262,0.002322917,0.005959668,0.007632795,0.002185082,0.007162398,0.01187579,0.005581058,0.0168544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003010273,"about_ca_system_score_gemma":0.01181008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01015654,"about_ca_topic_score_gemma":0.02172053,"domain_scores_codex":[0.9834222,0.009647717,0.002354379,0.001718728,0.002440551,0.0004164003],"domain_scores_gemma":[0.940681,0.04212463,0.002613026,0.0071568,0.006381379,0.001043019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003950873,0.0001907848,0.002853499,0.008688971,0.0007805998,0.0009770618,0.02423591,0.01209868,0.005660468,0.2141716,0.4026909,0.3272564],"study_design_scores_gemma":[0.0001970468,0.00003552537,0.001311808,0.001342248,0.0001668755,0.0003998484,0.002649216,0.03663697,0.002332212,0.2537362,0.7009918,0.0002002042],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.001948658,0.0005397405,0.899621,0.002142421,0.0004199116,0.002636444,0.04076053,0.03952112,0.01241014],"genre_scores_gemma":[0.007126748,0.0002901435,0.9608316,0.000265869,0.00004524394,0.008475827,0.01433284,0.004830079,0.003801621],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.04851327,"threshold_uncertainty_score":0.162293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07997970442216792,"score_gpt":0.4028001203780254,"score_spread":0.3228204159558574,"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."}}