{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003762344,0.0007748728,0.0008131104,0.0008809357,0.0005100051,0.0008574474,0.001495243,0.0009508908,0.001030582],"category_scores_gemma":[0.01457903,0.0004695862,0.0006647083,0.000713437,0.0006686995,0.00137663,0.000821315,0.0009148821,0.000274092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001163159,"about_ca_system_score_gemma":0.000782051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01635573,"about_ca_topic_score_gemma":0.01152886,"domain_scores_codex":[0.9990178,0.0005352614,0.00005138276,0.0001869304,0.0001250943,0.00008361493],"domain_scores_gemma":[0.9903687,0.007615255,0.0006585339,0.0005194522,0.0005853383,0.0002527235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002280538,0.0001200216,0.009850445,0.00004309992,0.00005289634,0.00008243964,0.0001143063,0.9603298,0.0009139319,0.007433929,0.0006129775,0.02021802],"study_design_scores_gemma":[0.000001799515,0.000005392727,0.0001717486,0.000001789875,0.000001739974,0.000003099708,0.00000530577,0.9988635,0.00009004961,0.0008131337,0.00004105665,0.000001480437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2243255,0.0002562795,0.7726542,0.0005349518,0.0000627074,0.0001731572,0.0003732481,0.0004466015,0.001173385],"genre_scores_gemma":[0.9503248,0.0001496887,0.04756238,0.00007141843,0.00009239639,0.0001629147,0.0006122196,0.00003399407,0.0009901547],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01635573,"threshold_uncertainty_score":0.03252107,"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."}}