{"id":"W3120906435","doi":"10.1140/epjds/s13688-020-00254-7","title":"Challenges when identifying migration from geo-located Twitter data","year":2021,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Geolocation; Suspect; Data science; Computer science; Set (abstract data type); Social media; Reliability (semiconductor); TRACE (psycholinguistics); Data set; Internet privacy; World Wide Web; Sociology; Artificial intelligence","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":[0.03410694,0.0004579969,0.0008165532,0.00606316,0.001299728,0.004413414,0.002220408,0.00166041,0.001854746],"category_scores_gemma":[0.2265846,0.0007046201,0.0005807636,0.009642182,0.001685237,0.004478403,0.003548816,0.001971047,0.002071487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001076433,"about_ca_system_score_gemma":0.001477834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01009182,"about_ca_topic_score_gemma":0.007952137,"domain_scores_codex":[0.9564514,0.03059114,0.003665089,0.002937572,0.00568354,0.0006712339],"domain_scores_gemma":[0.7519321,0.1849137,0.01839851,0.02633903,0.01741216,0.00100455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006923366,0.0002166092,0.6147408,0.002699418,0.0007132984,0.001060349,0.02168002,0.0190469,0.004311826,0.03155984,0.0280408,0.2752378],"study_design_scores_gemma":[0.00009891659,0.0002943154,0.4172259,0.004645566,0.00032543,0.00247618,0.05780677,0.1280169,0.01247303,0.1330617,0.2432536,0.0003217855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6075557,0.004294173,0.3156814,0.01805601,0.001272068,0.001244264,0.02879606,0.00135299,0.02174738],"genre_scores_gemma":[0.8775722,0.0009341434,0.1065269,0.001223551,0.0003827638,0.0007488357,0.01023372,0.0002069964,0.002170868],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03410694,"threshold_uncertainty_score":0.1803769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3333258322916927,"score_gpt":0.4153275156938945,"score_spread":0.08200168340220182,"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."}}