{"id":"W4391621552","doi":"10.2139/ssrn.4719403","title":"Comprehensive Analysis of Transformer Networks in Identifying Informative Sentences Containing Customer Needs","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Transformer; Computer science; Customer needs; Natural language processing; Business; Engineering; Marketing; Electrical engineering","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":[0.001969648,0.0007629989,0.0005336844,0.003730065,0.0007528924,0.001226301,0.000581186,0.0008548969,0.002882004],"category_scores_gemma":[0.008697625,0.0003083328,0.0005084104,0.002500109,0.0003292905,0.002876773,0.0007936505,0.0009270638,0.001191808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005020112,"about_ca_system_score_gemma":0.001046588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002660104,"about_ca_topic_score_gemma":0.006552298,"domain_scores_codex":[0.9990728,0.0004009686,0.00006068235,0.0001848565,0.0002017105,0.00007887441],"domain_scores_gemma":[0.9916038,0.006623833,0.0003565294,0.0003679497,0.0008800714,0.0001678643],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001982543,0.0007531477,0.04834671,0.00134003,0.0005257507,0.001987577,0.00197983,0.0794128,0.08592621,0.02724168,0.02073839,0.7297654],"study_design_scores_gemma":[0.00004792615,0.0002625469,0.02363699,0.00008676228,0.0004636673,0.0009160555,0.0008472071,0.9168199,0.02027393,0.02863579,0.007958315,0.00005097588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5664051,0.003411157,0.4076837,0.001107645,0.0001048882,0.000372947,0.007571613,0.002416915,0.01092606],"genre_scores_gemma":[0.9183326,0.0009257699,0.07016623,0.0000883193,0.0001022631,0.0001410812,0.006992274,0.000167328,0.003083997],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003730065,"threshold_uncertainty_score":0.01041663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0169723683184902,"score_gpt":0.3042278254050341,"score_spread":0.2872554570865439,"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."}}