{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006775019,0.00005150435,0.000143477,0.00008547192,0.0000992458,0.00003425926,0.0002942286,0.0000474742,0.0001662171],"category_scores_gemma":[0.0004647631,0.0000497086,0.000007552133,0.0004720287,0.0001663686,0.0001926205,0.0002412927,0.00010761,0.000001072887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001989159,"about_ca_system_score_gemma":0.0001306971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003652081,"about_ca_topic_score_gemma":0.01520104,"domain_scores_codex":[0.9991068,0.0002098737,0.0002091135,0.0002040087,0.0001561319,0.0001140292],"domain_scores_gemma":[0.9993314,0.0002756551,0.00005840418,0.0002478098,0.00005574833,0.00003103199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006530088,0.0002606299,0.1626782,0.0001023985,0.0002790006,0.00002332627,0.02174843,0.0001439105,0.0001320703,0.4569975,0.2894069,0.06816227],"study_design_scores_gemma":[0.0008932811,0.00002071621,0.1396325,0.00007178429,0.0001459316,7.111008e-7,0.004957327,0.01730049,0.00003516009,0.2244748,0.6122591,0.0002081478],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2271648,0.001537944,0.3297817,0.003731748,0.0006553876,0.0006107751,0.4332783,0.00005390959,0.003185514],"genre_scores_gemma":[0.8503853,0.0001463358,0.0890021,0.0009217209,0.00005785444,0.000003248448,0.05889522,0.000008273823,0.0005799358],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6232206,"threshold_uncertainty_score":0.8482537,"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."}}