{"id":"W2569424766","doi":"10.1186/s13673-016-0084-z","title":"Activity-based Twitter sampling for content-based and user-centric prediction models","year":2017,"lang":"en","type":"article","venue":"Human-centric Computing and Information Sciences","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Predictability; Sampling (signal processing); Social media; Focus (optics); Data mining; Sample (material); Experience sampling method; Data science; Machine learning; World Wide Web; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002349453,0.0001247978,0.0001827797,0.0003199453,0.00780797,0.001527786,0.0003008097,0.00007835751,0.00001879825],"category_scores_gemma":[0.0004614371,0.0001154491,0.0000686987,0.0002577136,0.0007294392,0.002232887,0.00004651315,0.00009558318,0.000002879259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007504292,"about_ca_system_score_gemma":0.0002372536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002348641,"about_ca_topic_score_gemma":0.000272867,"domain_scores_codex":[0.9985092,0.00009412107,0.0003477024,0.0002524199,0.0004580319,0.0003385844],"domain_scores_gemma":[0.9985504,0.0003957465,0.0004488674,0.0001938223,0.000280276,0.0001308887],"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":[0.0001365107,0.0004135701,0.1897309,0.0005656529,0.00008721971,6.51697e-7,0.02523281,0.1037045,0.0001560733,0.06199985,0.000976116,0.6169962],"study_design_scores_gemma":[0.001113358,0.00008704693,0.0242224,0.0000730375,0.00003916372,2.432838e-7,0.003043797,0.964913,0.00007004211,0.0004501054,0.005791757,0.0001960325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6128659,0.00004149497,0.3842191,0.001095548,0.0001492125,0.0003877627,0.00001178975,0.00007281039,0.001156388],"genre_scores_gemma":[0.9982538,0.00001966629,0.001120272,0.0004114248,0.0001193073,0.00001247834,0.00001755883,0.000003038056,0.00004252045],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8612085,"threshold_uncertainty_score":0.9995087,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1672333314923839,"score_gpt":0.3738017839738342,"score_spread":0.2065684524814503,"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."}}