{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001647848,0.0001083877,0.0001956824,0.0002309381,0.002900333,0.0002159847,0.001629405,0.00002274153,0.0002706053],"category_scores_gemma":[0.0003552384,0.00007205446,0.0004009545,0.001275467,0.0001385637,0.0002028374,0.0006650299,0.0002756003,0.000008119102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000208388,"about_ca_system_score_gemma":0.00003550332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001755693,"about_ca_topic_score_gemma":0.00005039763,"domain_scores_codex":[0.9981291,0.0001494142,0.0003734918,0.0002366329,0.0009372852,0.000174025],"domain_scores_gemma":[0.9978759,0.001042273,0.0005070298,0.0002217914,0.0003171521,0.00003582297],"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":[0.0001666922,0.0006901192,0.01126169,0.00004115318,0.002847062,7.824016e-7,0.03038829,0.1791376,0.0004501612,0.6607906,0.03104617,0.08317975],"study_design_scores_gemma":[0.0005919762,0.0003245728,0.0596584,0.00006424575,0.001176378,0.000009686335,0.01469754,0.1813595,0.0003678095,0.6821853,0.05903118,0.0005334652],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9706594,0.00002678777,0.002556158,0.01157919,0.0009827405,0.0003613638,0.000005008842,0.00008155954,0.01374781],"genre_scores_gemma":[0.9945369,0.000002384054,0.003431254,0.000299421,0.0002742634,0.00004025976,0.000004775711,0.000007691439,0.00140303],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08264628,"threshold_uncertainty_score":0.9983978,"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."}}