{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009799724,0.002044625,0.001667493,0.005562925,0.001541625,0.005119699,0.001874215,0.001881694,0.001622642],"category_scores_gemma":[0.04798796,0.001220961,0.001857604,0.003592884,0.001366361,0.008371036,0.002919619,0.003042285,0.0009919925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001918238,"about_ca_system_score_gemma":0.001364816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008116923,"about_ca_topic_score_gemma":0.009254646,"domain_scores_codex":[0.9945548,0.003372809,0.000329135,0.0008834446,0.0005985686,0.0002612408],"domain_scores_gemma":[0.9670581,0.02760967,0.001152161,0.001916193,0.001901002,0.0003629486],"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":[0.001825255,0.0004382481,0.03151545,0.001090519,0.000697681,0.0008939439,0.01035794,0.3435694,0.01092581,0.07929463,0.01392222,0.505469],"study_design_scores_gemma":[0.00003398683,0.00003701962,0.001709271,0.00005295634,0.0000579579,0.00006473723,0.0005121361,0.9431258,0.001611002,0.04966113,0.00309461,0.00003940225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07631307,0.002287699,0.915199,0.001099622,0.0001889278,0.0001340281,0.0006038317,0.00164534,0.002528428],"genre_scores_gemma":[0.7254445,0.001792083,0.2660588,0.0002931156,0.0007419508,0.000305723,0.002375871,0.0006300086,0.002358038],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009799724,"threshold_uncertainty_score":0.05182648,"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."}}