{"id":"W2576201175","doi":"","title":"Discovering Relevant Hashtags for Health Concepts: A Case Study of Twitter","year":2016,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thomson Reuters (Canada)","funders":"","keywords":"Computer science; Search engine indexing; Baseline (sea); Cluster analysis; Information retrieval; Social media; Word (group theory); Natural language processing; Artificial intelligence; Data science; World Wide Web; Linguistics","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":[0.0006494205,0.0001763479,0.0002960192,0.0002399345,0.0001621133,0.00007774543,0.0006293086,0.00004680061,0.0000328407],"category_scores_gemma":[0.0004446402,0.0001294776,0.00008590865,0.0003704631,0.0001137401,0.0004817258,0.0001273958,0.00009761561,0.00002119325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001713363,"about_ca_system_score_gemma":0.0002867841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000125473,"about_ca_topic_score_gemma":0.0004205715,"domain_scores_codex":[0.9977708,0.0001011596,0.0006963488,0.0005522319,0.0006092938,0.0002701239],"domain_scores_gemma":[0.9977849,0.0005587689,0.00036816,0.0004061537,0.000792928,0.00008911957],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004672485,0.0005949838,0.00007754128,0.00001287968,0.0000341067,0.00003295467,0.002719512,0.0003018763,0.003833623,0.7117636,0.0001483081,0.2804339],"study_design_scores_gemma":[0.0004267312,0.004615711,0.000196526,0.0004044492,0.00002136263,0.0001334493,0.006349756,0.1211429,0.1317112,0.7332522,0.0008353141,0.0009103942],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06189565,0.0000101425,0.9343851,0.002732156,0.00009617804,0.0005653545,0.0000172074,0.000103589,0.0001946019],"genre_scores_gemma":[0.9769977,0.00001134715,0.02238269,0.0003330643,0.00004897033,0.0001277514,0.000001346132,0.000009900367,0.00008724225],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9151021,"threshold_uncertainty_score":0.5279945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1941573157858804,"score_gpt":0.4542740632284499,"score_spread":0.2601167474425695,"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."}}