{"id":"W4413009343","doi":"10.1016/j.dib.2025.111960","title":"A large-scale dataset of AI-related tweets: Structure and descriptive statistics","year":2025,"lang":"en","type":"article","venue":"Data in Brief","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal; Polytechnique Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Polytechnique Montréal","keywords":"Descriptive statistics; Scale (ratio); Computer science; Statistics; Data science; Information retrieval; Geography; Mathematics; Cartography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002314141,0.0006042787,0.0006126308,0.006493324,0.001212114,0.001466713,0.001022268,0.001328854,0.005758554],"category_scores_gemma":[0.01745813,0.0002852219,0.0004952347,0.009935255,0.000670958,0.001327979,0.00210668,0.00117888,0.008741107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001270797,"about_ca_system_score_gemma":0.002341723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009254249,"about_ca_topic_score_gemma":0.01505105,"domain_scores_codex":[0.9965521,0.0008987038,0.0005711493,0.0005930812,0.001087706,0.0002971726],"domain_scores_gemma":[0.9847356,0.00740413,0.001840678,0.00223898,0.0031991,0.0005815219],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0009677911,0.0008078482,0.1192014,0.003136236,0.0002470004,0.001261731,0.005425502,0.005038162,0.01100701,0.00900636,0.749558,0.09434294],"study_design_scores_gemma":[0.000213026,0.0002704287,0.2901754,0.0005948481,0.0001167273,0.001022047,0.007157881,0.01405051,0.006335435,0.00732307,0.6724991,0.0002414979],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.05971686,0.0002274094,0.004428698,0.0007923202,0.0001740193,0.0006294745,0.9288901,0.0007252386,0.00441582],"genre_scores_gemma":[0.05308977,0.0001725289,0.0112518,0.000203443,0.0001346428,0.001984045,0.9308869,0.0001950475,0.002081766],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9935067,"threshold_uncertainty_score":0.01926428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03068471305990503,"score_gpt":0.3807641222503054,"score_spread":0.3500794091904003,"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."}}