{"id":"W4296169898","doi":"10.2139/ssrn.4214955","title":"Using the Social Network Structure of Influencers to Understand and Predict User Engagement","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Knowledge Management and Sharing","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Influencer marketing; Social network (sociolinguistics); Social network analysis; User engagement; Network structure; Data science; Computer science; Social media; Internet privacy; World Wide Web; Sociology; Psychology; Business; Marketing; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001132276,0.0003077933,0.0003116178,0.003477206,0.0007050998,0.001745765,0.0002978613,0.0006290204,0.002868544],"category_scores_gemma":[0.0143441,0.0001776145,0.0003760174,0.002454482,0.0003857757,0.003222806,0.000969819,0.0005487072,0.0005744324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004934662,"about_ca_system_score_gemma":0.0003995765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004670748,"about_ca_topic_score_gemma":0.008378607,"domain_scores_codex":[0.9990589,0.0003686662,0.00006103106,0.0001505546,0.0002552758,0.0001056447],"domain_scores_gemma":[0.9865003,0.009983739,0.001727534,0.0004920957,0.0007233444,0.000572885],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002021511,0.0002082991,0.954957,0.00009715357,0.0002207418,0.00009715959,0.003169538,0.002263816,0.002056385,0.001951258,0.0005062401,0.03427025],"study_design_scores_gemma":[0.00001954867,0.0003260425,0.9207756,0.00005503851,0.0001603674,0.0002902607,0.004265484,0.06282002,0.001082594,0.007403579,0.002763009,0.00003853922],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9872947,0.000137138,0.004936506,0.0001783961,0.00001078471,0.00004937619,0.0004791198,0.00005010489,0.006863847],"genre_scores_gemma":[0.9986172,0.00004402914,0.0008304339,0.000008436867,0.000008921166,0.00002355746,0.000165216,0.000004926623,0.0002972139],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004670748,"threshold_uncertainty_score":0.009596229,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03314632266804401,"score_gpt":0.3142977509402137,"score_spread":0.2811514282721697,"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."}}