{"id":"W4321488394","doi":"10.1145/3539597.3573033","title":"DisKeyword: Tweet Corpora Exploration for Keyword Selection","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Social media; Selection (genetic algorithm); Information retrieval; Task (project management); License; GRASP; Keyword search; Artificial intelligence; World Wide Web; Natural language processing","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":[],"consensus_categories":[],"category_scores_codex":[0.001481469,0.002004516,0.001391208,0.004763225,0.001247756,0.002773014,0.001662017,0.00114562,0.02128759],"category_scores_gemma":[0.01082758,0.0007941422,0.001163639,0.004149033,0.0005388609,0.004434672,0.002912487,0.001268557,0.01851999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000612983,"about_ca_system_score_gemma":0.001537076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003003438,"about_ca_topic_score_gemma":0.008902439,"domain_scores_codex":[0.9990049,0.0002102086,0.00009427578,0.0003082209,0.0002891673,0.00009322561],"domain_scores_gemma":[0.9969515,0.001742853,0.0001628516,0.0005117885,0.0004574721,0.0001736454],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001228442,0.0002705757,0.004854908,0.001989566,0.0003841594,0.000484659,0.001413228,0.005031469,0.03638751,0.007676304,0.2188427,0.7214365],"study_design_scores_gemma":[0.0008251925,0.0004351179,0.005536894,0.0003265166,0.0002419789,0.001283293,0.001831041,0.5754772,0.07255694,0.04364577,0.2975868,0.0002532923],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03543067,0.003311289,0.5734131,0.001699763,0.000968036,0.0008203447,0.03084377,0.3419953,0.01151779],"genre_scores_gemma":[0.09027897,0.001068862,0.8498138,0.0005317734,0.0002655092,0.0009482043,0.02903836,0.01575832,0.01229623],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02128759,"threshold_uncertainty_score":0.07121408,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04859705573421192,"score_gpt":0.3217964994498611,"score_spread":0.2731994437156491,"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."}}