{"id":"W4405113218","doi":"10.1016/j.procs.2024.11.126","title":"NLP and Topic Modeling with LDA, LSA, and NMF for Monitoring Psychosocial Well-being in Monthly Surveys","year":2024,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Information retrieval; Topic model; Data science","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":[0.002697116,0.00008840053,0.0001292252,0.0001998619,0.0004642238,0.0004998486,0.0001839995,0.00003231648,0.000001419675],"category_scores_gemma":[0.00006382608,0.0000766769,0.00002200526,0.0008847088,0.0002404009,0.0005129453,0.00007074153,0.00008952189,7.816899e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005017722,"about_ca_system_score_gemma":0.0002245603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003996369,"about_ca_topic_score_gemma":0.0004139278,"domain_scores_codex":[0.9987253,0.00007793652,0.0001441141,0.0004352486,0.0003424697,0.0002749501],"domain_scores_gemma":[0.9993865,0.0003135531,0.00002410721,0.00005274768,0.000123151,0.00009986705],"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":[0.00001470453,0.00004497068,0.1126324,0.0001704368,0.00002704527,0.00001104953,0.05300503,0.01324748,0.0001060883,0.06138817,0.00002028741,0.7593324],"study_design_scores_gemma":[0.0001389577,0.00003783487,0.01785916,0.0001024534,0.000009406313,0.000001199925,0.0002529088,0.9473714,0.00002366608,0.0337942,0.0002629478,0.0001459313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4984392,0.0003515439,0.4989795,0.000754746,0.0004352905,0.0001618226,5.034788e-7,0.00004605268,0.0008313106],"genre_scores_gemma":[0.9252195,0.00003620176,0.07411241,0.000026548,0.0005383525,0.00001711886,3.859044e-7,0.000004924751,0.00004460723],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9341239,"threshold_uncertainty_score":0.4820051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02895404700687553,"score_gpt":0.3523990624763297,"score_spread":0.3234450154694542,"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."}}