{"id":"W4293863214","doi":"10.1109/siu55565.2022.9864897","title":"Natural Language Processing-Based Product Category Classification Model for E-Commerce","year":2022,"lang":"en","type":"article","venue":"2022 30th Signal Processing and Communications Applications Conference (SIU)","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Stantec (Canada)","funders":"","keywords":"Computer science; Product (mathematics); Scope (computer science); Turkish; E-commerce; Dynamism; Natural language; World Wide Web; Data science; Artificial intelligence","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","sts"],"consensus_categories":[],"category_scores_codex":[0.0006846391,0.0002339848,0.0002508039,0.0003571354,0.003326056,0.0005245238,0.002353537,0.00004268742,0.00002686653],"category_scores_gemma":[0.00001875764,0.0002468309,0.00008922869,0.001331905,0.0001967922,0.0004901861,0.0006479388,0.0004333113,0.00000488602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009619804,"about_ca_system_score_gemma":0.0006578295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001933117,"about_ca_topic_score_gemma":0.00002294,"domain_scores_codex":[0.9979618,0.0001562516,0.000482506,0.0007049996,0.0003798593,0.0003146149],"domain_scores_gemma":[0.9973867,0.0001672526,0.0004319646,0.001505364,0.0004105706,0.00009816712],"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":[0.00002114265,0.0005301114,0.0002301262,0.00015246,0.00003206288,2.104726e-7,0.003853158,0.003719656,0.007046726,0.07274432,0.0007013789,0.9109687],"study_design_scores_gemma":[0.0003158878,0.00003108771,0.0001699833,0.00002193727,0.00004671557,0.000004099465,0.001861058,0.9865673,0.000152878,0.001462556,0.009060748,0.0003058083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006725252,0.008306826,0.9817885,0.006968422,0.00002242958,0.000856279,0.00003044855,0.0002601358,0.001094388],"genre_scores_gemma":[0.9290471,0.00006775867,0.06480829,0.0004658765,0.00003409166,0.004064332,0.0004730069,0.00002242021,0.001017105],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9828476,"threshold_uncertainty_score":0.9999984,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05933879780773499,"score_gpt":0.3146798987618716,"score_spread":0.2553411009541366,"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."}}