{"id":"W2178827989","doi":"10.1609/icwsm.v9i1.14651","title":"Exemplar-Based Topic Detection in Twitter Streams","year":2021,"lang":"en","type":"article","venue":"Proceedings of the International AAAI Conference on Web and Social Media","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Qatar National Research Fund; Fonds National de la Recherche Luxembourg","keywords":"Computer science; Benchmark (surveying); Set (abstract data type); Recall; Precision and recall; Context (archaeology); Meaning (existential); Data science; Focus (optics); Key (lock); Term (time); Information retrieval; Interpretation (philosophy); Artificial intelligence; Computer security; Psychology","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":[0.0000773565,0.00007186917,0.0001168558,0.00004972651,0.00004567311,0.00004853534,0.0001605772,0.00002888009,0.0001955037],"category_scores_gemma":[0.00002084525,0.00005925142,0.0000637069,0.00009990463,0.00003686808,0.0000506665,0.0000629764,0.0001272972,9.99484e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002491201,"about_ca_system_score_gemma":0.00004417796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002807959,"about_ca_topic_score_gemma":0.00008713378,"domain_scores_codex":[0.9994425,0.000006353008,0.0001445644,0.0001342373,0.0001915085,0.00008084629],"domain_scores_gemma":[0.9996412,0.00003921619,0.00009317425,0.00003047294,0.000180854,0.00001507095],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009906942,0.000431887,0.2834853,0.00003915115,0.000174981,0.000001473579,0.003718373,0.000003994503,0.1828025,0.3301549,0.001478087,0.1976103],"study_design_scores_gemma":[0.002191785,0.00007678429,0.1218757,0.0004482046,0.00009947987,0.000001969863,0.006900253,0.01416795,0.5791852,0.266641,0.007810141,0.0006015173],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.984097,0.000004114103,0.00003974218,0.002618716,0.0001172428,0.00004580784,0.000007094693,0.000009595893,0.01306067],"genre_scores_gemma":[0.9994312,0.000002677858,0.00007221175,0.00009476252,0.000230251,0.00001562183,0.000005061937,0.000004112981,0.0001440933],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3963827,"threshold_uncertainty_score":0.2416203,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02535777233679787,"score_gpt":0.2622715350143426,"score_spread":0.2369137626775447,"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."}}