{"id":"W2770119650","doi":"10.1002/asi.23980","title":"Improving interpretations of topic modeling in microblogs","year":2017,"lang":"en","type":"article","venue":"Journal of the Association for Information Science and Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; McGill University; Ontario Tech University; Concordia University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; King Saud University; Saudi Arabian Cultural Bureau; CRC Health Group","keywords":"Computer science; Perplexity; Topic model; Information retrieval; Microblogging; WordNet; Social media; Process (computing); Latent Dirichlet allocation; Coherence (philosophical gambling strategy); Natural language processing; Artificial intelligence; Data science; World Wide Web; Language model","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":[0.001591878,0.00003464235,0.0001087106,0.0006369776,0.000262754,0.0001435031,0.001210492,0.00005227566,9.258675e-8],"category_scores_gemma":[0.003535454,0.00002515818,0.00003527306,0.0004966231,0.00009514194,0.004375622,0.0002431277,0.0001025793,1.860719e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001616152,"about_ca_system_score_gemma":0.0001388207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007798694,"about_ca_topic_score_gemma":0.000009973252,"domain_scores_codex":[0.999216,0.000006726676,0.0003930732,0.00004716059,0.0002421658,0.00009487521],"domain_scores_gemma":[0.9970284,0.00003859029,0.001531285,0.0002430291,0.001147017,0.00001165562],"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":[0.00000896883,0.00004396843,0.06042606,0.00003798161,0.00003506683,2.28702e-7,0.003222932,0.00178687,0.03921221,0.4435845,0.00008665003,0.4515546],"study_design_scores_gemma":[0.0007635803,0.0001158706,0.006845902,0.00009038963,0.00002020977,0.00001662283,0.0004836646,0.7924553,0.06132073,0.1368401,0.0009218046,0.0001259397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2130345,0.0000204934,0.7801721,0.00598255,0.0001896999,0.0001337293,0.000001062243,0.0000175327,0.000448276],"genre_scores_gemma":[0.9725471,0.00001136443,0.02737422,0.00004918729,0.000004120643,0.000002558912,4.825371e-8,6.403827e-7,0.00001080825],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7906684,"threshold_uncertainty_score":0.4232524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01099534156772924,"score_gpt":0.2826981526934637,"score_spread":0.2717028111257345,"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."}}