{"id":"W1014449310","doi":"10.1609/icwsm.v6i1.14340","title":"Homophily and Latent Attribute Inference: Inferring Latent Attributes of Twitter Users from Neighbors","year":2021,"lang":"en","type":"article","venue":"Proceedings of the International AAAI Conference on Web and Social Media","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":319,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Homophily; Assortativity; Inference; Computer science; Context (archaeology); Instant messaging; Machine learning; Artificial intelligence; World Wide Web; Psychology; Social psychology; Geography; Complex network","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002835799,0.0001557913,0.0002668564,0.00007748565,0.0001276178,0.0001668561,0.0006006878,0.0001156518,0.00004156724],"category_scores_gemma":[0.0004721835,0.0001240655,0.00008119512,0.0001934587,0.0001668547,0.0002964834,0.0005901051,0.0002536535,0.000002357492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003724108,"about_ca_system_score_gemma":0.0001367587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002544428,"about_ca_topic_score_gemma":0.00001204436,"domain_scores_codex":[0.9986137,0.00002073573,0.0003513226,0.0003165691,0.0005167096,0.000180966],"domain_scores_gemma":[0.9984953,0.0002644082,0.0002944828,0.0000818162,0.0007906391,0.00007338984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00005046131,0.0001106058,0.3894997,0.00006844409,0.0001776707,0.000003395635,0.009969378,0.000004071659,0.0516297,0.5429531,0.0003374815,0.005196017],"study_design_scores_gemma":[0.001989599,0.0001188095,0.7092719,0.0007762314,0.00008450683,0.00001326719,0.002073355,0.01328657,0.1558644,0.1147543,0.001106438,0.0006606209],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9856766,0.00008954042,0.0004475163,0.01257758,0.0005703629,0.00008278795,0.00008499351,0.00002850094,0.0004420959],"genre_scores_gemma":[0.998622,0.0002022863,0.0006283386,0.0003357081,0.0001142235,0.000007183379,0.00001391926,0.000005899416,0.00007046562],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4281988,"threshold_uncertainty_score":0.5059243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06759890956918559,"score_gpt":0.2797267150628564,"score_spread":0.2121278054936708,"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."}}