{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001042757,0.0009002523,0.0008757531,0.005200443,0.0007291273,0.001606032,0.0008406378,0.0008863219,0.0007965481],"category_scores_gemma":[0.004794332,0.0002955545,0.0007110673,0.002963179,0.0003697066,0.002224953,0.001089745,0.0006587756,0.001143441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004672581,"about_ca_system_score_gemma":0.0003456048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002636058,"about_ca_topic_score_gemma":0.003086171,"domain_scores_codex":[0.999022,0.0001875838,0.00008986271,0.0002918488,0.0002903209,0.0001182574],"domain_scores_gemma":[0.997754,0.0009897004,0.0003753666,0.0001690861,0.000590741,0.0001209772],"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":[0.001742688,0.0004495291,0.04003096,0.0009625059,0.000364591,0.001889301,0.001879541,0.05590039,0.1008147,0.01085307,0.02293229,0.7621805],"study_design_scores_gemma":[0.00002961179,0.000147495,0.01144459,0.00005400801,0.00008449124,0.000763262,0.0006937588,0.9380324,0.02883019,0.008366979,0.01148945,0.00006378153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2336593,0.003044574,0.7475941,0.0005654456,0.0002787749,0.0004378744,0.004079732,0.005972919,0.004367325],"genre_scores_gemma":[0.6455404,0.001736527,0.3391148,0.000153395,0.0005066471,0.000340188,0.009439115,0.0002316763,0.002937162],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005200443,"threshold_uncertainty_score":0.005514681,"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."}}