{"id":"W2578945560","doi":"","title":"Real Time Filtering of Tweets Using Wikipedia Concepts and Google Tri-gram Semantic Relatedness","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Information retrieval; n-gram; Semantic similarity; Word (group theory); Social media; World Wide Web; Natural language processing; Language model","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":[0.0005453297,0.0001911611,0.0003620736,0.0001042444,0.00006559748,0.0001313883,0.0005991042,0.000135013,0.00002243183],"category_scores_gemma":[0.0002200808,0.0001879911,0.00004075182,0.000363859,0.0001439212,0.0005037197,0.0004351654,0.0001953489,0.00002770786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006176149,"about_ca_system_score_gemma":0.0003370727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002436907,"about_ca_topic_score_gemma":0.000003385014,"domain_scores_codex":[0.9982616,0.0001085987,0.0004108146,0.0004727895,0.0004173889,0.0003287893],"domain_scores_gemma":[0.9986024,0.0001246829,0.0002068594,0.0005581833,0.0002881838,0.0002196835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007375663,0.0004747024,0.02176086,0.0008686349,0.000312977,0.0004948259,0.05148742,0.004263583,0.7154399,0.09467457,0.0008466554,0.1086383],"study_design_scores_gemma":[0.001376262,0.0002795748,0.00191283,0.0002868171,0.00003945873,0.00009211886,0.000159065,0.9754195,0.01525745,0.00441224,0.0002488773,0.0005157844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8783889,0.0001398393,0.1179811,0.00008330756,0.0003374529,0.000172115,0.000003338348,0.000142972,0.002750959],"genre_scores_gemma":[0.9834204,0.00002565896,0.01601733,0.00001726885,0.00006705023,9.483891e-7,0.000001901023,0.00001230214,0.0004371857],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9711559,"threshold_uncertainty_score":0.7666056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07837344284233229,"score_gpt":0.3094833050650553,"score_spread":0.231109862222723,"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."}}