{"id":"W3088547571","doi":"10.1145/3395027.3419589","title":"Short Text Stream Clustering via Frequent Word Pairs and Reassignment of Outliers to Clusters","year":2020,"lang":"en","type":"article","venue":"","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Outlier; Cluster analysis; Word (group theory); Similarity (geometry); Artificial intelligence; Margin (machine learning); Task (project management); Pattern recognition (psychology); Semantic similarity; Natural language processing; Data mining; Image (mathematics); Machine learning; Mathematics","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":[0.0001955329,0.000173154,0.000227938,0.00008824283,0.0000408501,0.00008891048,0.0008230614,0.00004755305,0.00001396419],"category_scores_gemma":[0.00003845416,0.0001576454,0.00003983842,0.0002667501,0.0000480517,0.000298308,0.001197306,0.00008589674,0.000009471798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005924914,"about_ca_system_score_gemma":0.00002296261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001054324,"about_ca_topic_score_gemma":0.00002759969,"domain_scores_codex":[0.9985847,0.00003928425,0.000309166,0.0005138631,0.0002955033,0.0002575124],"domain_scores_gemma":[0.9989867,0.00004919549,0.00005399334,0.0005729983,0.00003104433,0.0003060484],"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":[0.00003594658,0.00008094301,0.004817782,0.00007177718,0.00006250369,0.00003286678,0.004006962,0.0002070541,0.008021587,0.001516025,0.01946452,0.961682],"study_design_scores_gemma":[0.002219578,0.006239362,0.03739052,0.0008937034,0.0001500119,0.0001275237,0.004215082,0.629149,0.2825845,0.002492001,0.03048338,0.00405528],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01935364,0.00001374911,0.9730736,0.003431022,0.00006756523,0.0003184235,0.000009241871,0.0004355408,0.003297221],"genre_scores_gemma":[0.6848168,0.000005793113,0.3141914,0.0009066627,0.00001510445,0.00001593702,0.000002674767,0.000009558569,0.00003608304],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9576268,"threshold_uncertainty_score":0.6428594,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0269366959402034,"score_gpt":0.2528465641545121,"score_spread":0.2259098682143087,"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."}}