{"id":"W3087237611","doi":"10.1145/3274895.3274982","title":"Creating full individual-level location timelines from sparse social media data","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; National Science Foundation","keywords":"Timeline; Heuristics; Computer science; Social media; Inference; Baseline (sea); Geolocation; Global Positioning System; Data science; Data mining; Artificial intelligence; World Wide Web; Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002944198,0.000266319,0.000436345,0.0001601307,0.001224499,0.000487431,0.002003188,0.0006049041,0.0076872],"category_scores_gemma":[0.00322636,0.000272129,0.000122494,0.0003986836,0.000663529,0.0002686044,0.001217848,0.0004424208,0.0005896352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001871851,"about_ca_system_score_gemma":0.001550288,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1001047,"about_ca_topic_score_gemma":0.3909623,"domain_scores_codex":[0.9963854,0.0006184964,0.0006229136,0.0009963465,0.00102996,0.0003468853],"domain_scores_gemma":[0.9966112,0.0009627948,0.000433836,0.001149784,0.0006911673,0.0001512017],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000103461,0.001168413,0.01456823,0.0003135372,0.002134717,0.000007412866,0.472568,0.001008789,0.00007403868,0.00988663,0.1881706,0.3099962],"study_design_scores_gemma":[0.002759801,0.0001117947,0.2029946,0.00158895,0.008491685,6.039687e-7,0.2493088,0.1353263,0.0004532554,0.2760906,0.1150379,0.007835771],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6027896,0.001659408,0.2264811,0.01813542,0.006312459,0.002996069,0.01494127,0.002034998,0.1246497],"genre_scores_gemma":[0.9667435,0.00007104653,0.005924406,0.0002849129,0.009101125,0.00003964046,0.01668481,0.00002575929,0.00112476],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3639539,"threshold_uncertainty_score":0.9999731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.225285950918736,"score_gpt":0.3734886316382931,"score_spread":0.1482026807195571,"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."}}