{"id":"W3005532966","doi":"10.1108/ejm-02-2019-0219","title":"Making sense of text: artificial intelligence-enabled content analysis","year":2020,"lang":"en","type":"article","venue":"European Journal of Marketing","topic":"Consumer Behavior in Brand Consumption and Identification","field":"Business, Management and Accounting","cited_by":100,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria; Simon Fraser University","funders":"","keywords":"Content analysis; Computer science; Reliability (semiconductor); IBM; Originality; Content validity; Computer-aided; Artificial intelligence; Data science; Qualitative research","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":[0.02634015,0.0009058875,0.0007317555,0.01652666,0.002419928,0.01254077,0.002378159,0.001095352,0.005914813],"category_scores_gemma":[0.08699857,0.0005517645,0.0009365228,0.01121913,0.00648296,0.01769761,0.005715879,0.001690313,0.00183558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004238086,"about_ca_system_score_gemma":0.004704644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001945122,"about_ca_topic_score_gemma":0.001754185,"domain_scores_codex":[0.9668095,0.02316553,0.002290049,0.002293183,0.004910462,0.0005311919],"domain_scores_gemma":[0.8634363,0.1068567,0.006385827,0.008877362,0.01336354,0.001080282],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001742867,0.0002238359,0.01004042,0.003201182,0.0001476902,0.0005017197,0.08526035,0.001915585,0.007989179,0.09988891,0.01489292,0.7757638],"study_design_scores_gemma":[0.0001178068,0.0003489689,0.02133868,0.005537231,0.0002829639,0.001607518,0.1257785,0.05027147,0.02120921,0.4767519,0.2963413,0.0004144227],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08643347,0.002712928,0.823556,0.01058975,0.0007719607,0.007102109,0.002664447,0.003596673,0.0625726],"genre_scores_gemma":[0.2678149,0.001563573,0.7204761,0.0008491811,0.0003574151,0.002904104,0.001507433,0.0005289101,0.003998443],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02634015,"threshold_uncertainty_score":0.1393017,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1710871604752906,"score_gpt":0.2867851885525743,"score_spread":0.1156980280772837,"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."}}