{"id":"W4386763311","doi":"10.36227/techrxiv.24143706.v1","title":"GPT-4 as a Twitter Data Annotator: Unraveling Its Performance on a Stance Classification Task","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University; York University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Task (project management); Computer science; Natural language processing; Artificial intelligence; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0173924,0.002594754,0.001449605,0.003118495,0.002091254,0.002998215,0.002872543,0.004452451,0.00351366],"category_scores_gemma":[0.03182294,0.0006766766,0.001424737,0.002204529,0.00112909,0.004922445,0.004081277,0.003962383,0.005130668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002408095,"about_ca_system_score_gemma":0.002808945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02921543,"about_ca_topic_score_gemma":0.04278245,"domain_scores_codex":[0.9909768,0.005479077,0.0003616879,0.001862407,0.0008820391,0.0004379743],"domain_scores_gemma":[0.9765513,0.01627168,0.0007769797,0.002446893,0.002955724,0.0009974557],"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":[0.006906383,0.00217453,0.08867049,0.002123155,0.001608152,0.0008415778,0.003386998,0.09287897,0.02969326,0.003773446,0.1138082,0.6541349],"study_design_scores_gemma":[0.0002310901,0.0006481521,0.01246517,0.0001499952,0.0002119589,0.0002048146,0.001282387,0.9574627,0.01027028,0.004282848,0.01264118,0.0001495285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7150316,0.006594769,0.188467,0.01051031,0.003091741,0.001704736,0.01797102,0.03027754,0.02635126],"genre_scores_gemma":[0.7734392,0.0007453525,0.186234,0.001776114,0.0005407449,0.0009233287,0.02514517,0.001251131,0.009945039],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02921543,"threshold_uncertainty_score":0.09198087,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2535944618526218,"score_gpt":0.3486720213166273,"score_spread":0.09507755946400553,"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."}}