{"id":"W3120644806","doi":"","title":"Methodological Issues in Using Word Embeddings in a Sociolinguistic Perspective: The Case of Contact-Induced Semantic Variation Across Canadian Twitter Corpora","year":2020,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Variation (astronomy); Perspective (graphical); Computer science; Word (group theory); Natural language processing; Artificial intelligence; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05282013,0.0006512285,0.0008973928,0.005067789,0.007100509,0.009785349,0.004187637,0.001577152,0.00332977],"category_scores_gemma":[0.2085188,0.0008894776,0.000756418,0.01352236,0.009518879,0.00687898,0.006328352,0.002882843,0.0007537269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0080735,"about_ca_system_score_gemma":0.01728609,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.4736033,"about_ca_topic_score_gemma":0.6363684,"domain_scores_codex":[0.9557422,0.02582,0.003514259,0.00491617,0.00814052,0.001866743],"domain_scores_gemma":[0.8654407,0.07615107,0.007804211,0.01977322,0.02957547,0.001255431],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000586132,0.0002293398,0.1137186,0.002782831,0.001120986,0.001249615,0.1426098,0.01033534,0.02741201,0.4380686,0.02735986,0.2345269],"study_design_scores_gemma":[0.0001651257,0.0001773986,0.3328057,0.002032426,0.0006516431,0.001457229,0.1298306,0.03470187,0.02696202,0.2650162,0.2056123,0.0005874108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4725508,0.00412699,0.4234309,0.02527308,0.001345085,0.001251867,0.01166832,0.0005442387,0.05980872],"genre_scores_gemma":[0.8864345,0.0007674439,0.1019884,0.001143865,0.0002341152,0.001366939,0.003759878,0.0006377797,0.003667043],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5263966,"threshold_uncertainty_score":0.9416933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1371203814930111,"score_gpt":0.3997540574188897,"score_spread":0.2626336759258786,"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."}}