{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5178431,0.002869197,0.004683042,0.01845578,0.01470223,0.05562811,0.01163834,0.01099022,0.005739366],"category_scores_gemma":[0.6513807,0.004405585,0.002134372,0.01898025,0.08723706,0.09593831,0.03147575,0.02516265,0.002049903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02505394,"about_ca_system_score_gemma":0.05102476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01174212,"about_ca_topic_score_gemma":0.01323321,"domain_scores_codex":[0.4002103,0.5139257,0.01792883,0.01525146,0.04829825,0.004385555],"domain_scores_gemma":[0.12072,0.7906094,0.008898877,0.04854004,0.0264711,0.004760592],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000127707,0.0004342175,0.01124005,0.005836183,0.0003154716,0.0004491531,0.08164325,0.002715378,0.0003277063,0.7456361,0.01669662,0.1345783],"study_design_scores_gemma":[0.00007506741,0.0001138981,0.001543852,0.005901183,0.00005844723,0.000166265,0.0421999,0.005910388,0.0003094274,0.9089338,0.0346968,0.00009108147],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.03047839,0.02678699,0.362008,0.5260686,0.002218309,0.002325619,0.0009183997,0.0005153687,0.04868042],"genre_scores_gemma":[0.5247435,0.01496596,0.4271148,0.02060741,0.002162961,0.007836193,0.000532449,0.0005244705,0.001512269],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4821569,"threshold_uncertainty_score":0.5945853,"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."}}