{"id":"W4399765771","doi":"10.32920/26052508.v1","title":"Discovering Related Terms and Detecting Trends in Software Engineering Using Word Embeddings","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Word (group theory); Computer science; Software; Natural language processing; Data science; Artificial intelligence; Software engineering; Linguistics; Programming language; Philosophy","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":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.001407539,0.0007232102,0.0003942602,0.008729736,0.0004919234,0.001761263,0.0005307354,0.0008577671,0.00153608],"category_scores_gemma":[0.009632642,0.0002984028,0.0007922261,0.00859915,0.0004308923,0.003714043,0.001075231,0.0008765207,0.0008645357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004943202,"about_ca_system_score_gemma":0.0007064857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00283539,"about_ca_topic_score_gemma":0.005953363,"domain_scores_codex":[0.9987225,0.0003477203,0.0002513006,0.0003288376,0.0002700846,0.00007950959],"domain_scores_gemma":[0.9926969,0.004675779,0.0009845194,0.000525806,0.0009812565,0.0001355777],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003329554,0.0004213894,0.07584992,0.001488716,0.0002370078,0.0006952929,0.00373966,0.02996702,0.02454514,0.01011376,0.01206638,0.8405427],"study_design_scores_gemma":[0.00011781,0.0009282524,0.1111143,0.0005781151,0.000352621,0.001787878,0.007138377,0.7361414,0.02635822,0.05315103,0.06217479,0.0001573011],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6715873,0.003511046,0.3044084,0.001419032,0.0002917391,0.0003310503,0.009963854,0.003062097,0.005425477],"genre_scores_gemma":[0.6693832,0.001620037,0.3085425,0.0001156824,0.0001099779,0.0003753379,0.01682897,0.000239385,0.00278497],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9912702,"threshold_uncertainty_score":0.007443845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0116731118877704,"score_gpt":0.2734794675310537,"score_spread":0.2618063556432834,"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."}}