{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002349626,0.00009617185,0.0001156617,0.000232512,0.0001340384,0.0001322479,0.0003410209,0.0000439978,0.000007065101],"category_scores_gemma":[0.00004921625,0.00008840494,0.00006387207,0.001448156,0.0000140285,0.001249104,0.00009454546,0.00005022406,0.00009933522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004086125,"about_ca_system_score_gemma":0.0000217802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000014271,"about_ca_topic_score_gemma":0.00002733968,"domain_scores_codex":[0.9990993,0.00002236507,0.0001795091,0.0003202443,0.0001693236,0.0002092771],"domain_scores_gemma":[0.9993688,0.00008642994,0.00008357187,0.0002886758,0.0001290277,0.00004344842],"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":[0.0000108978,0.00005432365,0.0009360071,0.00001371761,0.00003340566,0.000002380942,0.0002608788,0.006560773,0.005661344,0.7694439,0.06957329,0.1474491],"study_design_scores_gemma":[0.0001489536,0.0001125383,0.0004431312,0.000004888907,0.000008458312,0.000001343247,0.00003840824,0.7524168,0.01351181,0.2020663,0.03104051,0.000206746],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001380218,0.000006681068,0.9938809,0.0009202903,0.0001359376,0.0002705187,9.734708e-7,0.00248462,0.000919822],"genre_scores_gemma":[0.5254996,0.00005315832,0.4654914,0.0001906655,0.0001444375,0.0004615838,0.00005413529,0.00002240091,0.008082598],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7458561,"threshold_uncertainty_score":0.3605049,"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."}}