{"id":"W1992440927","doi":"10.1109/tkde.2014.2359672","title":"Incorporating Social Role Theory into Topic Models for Social Media Content Analysis","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Key Research and Development Program of China; Engineering and Physical Sciences Research Council; National Natural Science Foundation of China","keywords":"Social media; Computer science; Microblogging; Generative model; Focus (optics); Topic model; Regularization (linguistics); Data science; Process (computing); World Wide Web; Information retrieval; Generative grammar; Artificial intelligence","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":[0.0005160914,0.0001376504,0.0002437797,0.0002134712,0.0003523603,0.0001069488,0.0004725849,0.00008252395,0.000001274919],"category_scores_gemma":[0.0000136916,0.0001325366,0.00008825614,0.0003233371,0.00001976593,0.0004287004,0.00001359593,0.0001206259,0.000003296483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003186954,"about_ca_system_score_gemma":0.0000199974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001856599,"about_ca_topic_score_gemma":0.000114692,"domain_scores_codex":[0.9990963,0.00004776707,0.0002153969,0.0003579402,0.0001012422,0.0001812933],"domain_scores_gemma":[0.9991835,0.0003202034,0.00004521238,0.000337905,0.00005114764,0.00006199816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004446869,0.0003330523,0.00003704409,0.000330411,0.001285972,0.000001786649,0.05787529,0.05675768,0.009690684,0.2385054,0.0004243369,0.6347139],"study_design_scores_gemma":[0.0002789734,0.00002307336,0.00004101272,0.00001462423,0.00008705148,9.76832e-7,0.0001766249,0.9962506,0.0009428223,0.001358243,0.0006535567,0.0001724427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003146202,0.0001657948,0.9957112,0.00006782438,0.0004993561,0.00008682329,0.00003930881,0.0001412139,0.0001422438],"genre_scores_gemma":[0.9894822,0.000004553241,0.01006922,0.00001423975,0.0003020756,0.0000407139,0.00002292678,0.00001178615,0.00005224697],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9863361,"threshold_uncertainty_score":0.5404687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06034266008053929,"score_gpt":0.2760029146332962,"score_spread":0.2156602545527569,"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."}}