{"id":"W4399190889","doi":"10.3389/fdata.2024.1379921","title":"From theory to practice: insights and hurdles in collecting social media data for social science research","year":2024,"lang":"en","type":"article","venue":"Frontiers in Big Data","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Dalhousie University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Social media; Scripting language; Data science; Data collection; Public relations; Set (abstract data type); Frontier; Social computing; World Wide Web; Computer science; Sociology; Political science; Social science","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":[],"consensus_categories":[],"category_scores_codex":[0.004076187,0.00011208,0.0002349329,0.0005953806,0.0004397275,0.0004254456,0.001753462,0.00004584877,0.00001123312],"category_scores_gemma":[0.0007251034,0.0001118335,0.00001735409,0.001903927,0.0003224142,0.0008164834,0.002736186,0.0003675073,0.000001879923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001256443,"about_ca_system_score_gemma":0.0003429395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005394347,"about_ca_topic_score_gemma":0.0003546079,"domain_scores_codex":[0.9978753,0.0002554781,0.0002481603,0.0008695349,0.000376863,0.000374635],"domain_scores_gemma":[0.9978179,0.001240503,0.00004377503,0.0007666837,0.00007702137,0.00005412168],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008964088,0.00007023062,0.001756699,0.00001271602,0.00006898075,0.00000526246,0.007922005,6.173833e-7,0.0002454498,0.01277636,0.450162,0.52689],"study_design_scores_gemma":[0.0004102842,0.00002072436,0.001476785,0.0001339204,0.00007217854,1.642232e-7,0.02440399,0.02604399,0.0001455623,0.3693585,0.5776016,0.0003322416],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08779833,0.006218819,0.8721437,0.005915427,0.004726031,0.002632797,0.01093354,0.0002347469,0.009396607],"genre_scores_gemma":[0.9079993,0.00003295909,0.08542269,0.00005399016,0.003863168,0.00007666499,0.002437975,0.00003156843,0.0000816724],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.820201,"threshold_uncertainty_score":0.4560437,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2024012015999186,"score_gpt":0.4471566180623417,"score_spread":0.2447554164624231,"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."}}