{"id":"W7134950890","doi":"10.1109/icdmw69685.2025.00184","title":"Predicting Interview Engagement in Real-Time Recruitment: Class Imbalance and Behavioral Feature Analysis","year":2025,"lang":"","type":"article","venue":"","topic":"Employer Branding and e-HRM","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada); University of Toronto","funders":"Iran Telecommunication Research Center","keywords":"Class (philosophy); Feature (linguistics); Interview; Affect (linguistics)","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":[0.005423095,0.0007562725,0.0007620669,0.001305959,0.0005977987,0.001002951,0.001008377,0.0008308237,0.001601954],"category_scores_gemma":[0.01020614,0.0001916499,0.0007168343,0.001083918,0.0002941584,0.001150365,0.001375766,0.001342028,0.0009990209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007456978,"about_ca_system_score_gemma":0.001014625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007727048,"about_ca_topic_score_gemma":0.008780756,"domain_scores_codex":[0.9982781,0.0008033396,0.00007187365,0.0004063053,0.0002199004,0.0002204491],"domain_scores_gemma":[0.9962684,0.002354637,0.0003561687,0.0004203315,0.0003173803,0.0002830746],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00123893,0.001570849,0.5747324,0.0001254209,0.00024506,0.000114063,0.000609354,0.1001084,0.00364424,0.000976034,0.01209969,0.3045356],"study_design_scores_gemma":[0.0000368253,0.0002544673,0.1126021,0.00002667353,0.00003990005,0.000048509,0.0004899614,0.8797931,0.002304659,0.001844146,0.002530455,0.00002924026],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.946748,0.0002855702,0.04765346,0.0007966249,0.00008875316,0.0001486744,0.001632903,0.0008671255,0.001778894],"genre_scores_gemma":[0.9775656,0.00006296054,0.0174871,0.0001343905,0.00004961417,0.0001614677,0.00310066,0.0000363443,0.001401815],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007727048,"threshold_uncertainty_score":0.02868044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06396455915343534,"score_gpt":0.3209103366465943,"score_spread":0.2569457774931589,"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."}}