{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002003268,0.0004675403,0.001285402,0.004766002,0.0001178467,0.0003219034,0.001785783,0.0003035863,0.000008417293],"category_scores_gemma":[0.00002349946,0.0004203306,0.0009736812,0.00503675,0.0001220499,0.0007727925,0.0007007076,0.006998667,0.000005851581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001430379,"about_ca_system_score_gemma":0.00167725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003096272,"about_ca_topic_score_gemma":0.001618502,"domain_scores_codex":[0.9951696,0.0002099959,0.001427105,0.0004703843,0.0006965493,0.0020264],"domain_scores_gemma":[0.9978338,0.0001835218,0.0009430654,0.0005342926,0.0004114343,0.00009384209],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009256655,0.000128168,0.004703624,0.0002384107,0.02048594,0.00006118877,0.02052466,0.4387908,0.0002340558,0.3737843,0.00003355528,0.1409228],"study_design_scores_gemma":[0.000401149,0.0001940495,0.0008877222,0.0006611688,0.002190141,0.0001003703,0.01344565,0.5684808,0.0002674265,0.4123978,0.0001549804,0.0008187878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0505149,0.009853718,0.9380514,0.0001999579,0.0002778336,0.0002456937,0.000004200646,0.0001337203,0.0007185598],"genre_scores_gemma":[0.9854811,0.0104928,0.003730001,0.00007337672,0.00006898914,0.00002501012,0.00001787152,0.00002352217,0.0000873574],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9349661,"threshold_uncertainty_score":0.9998249,"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."}}