{"id":"W2974657091","doi":"10.4018/ijossp.2019070103","title":"A Topic Modeling Based Approach for Enhancing Corpus Querying","year":2019,"lang":"en","type":"article","venue":"International Journal of Open Source Software and Processes","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Query expansion; Ranking (information retrieval); Information retrieval; Query optimization; Process (computing); Selection (genetic algorithm); Web query classification; Web search query; Data mining; Query language; Sargable; Quality (philosophy); Search engine; Machine learning","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":[0.000414452,0.000105617,0.0002252822,0.0001803529,0.00006566045,0.000565741,0.001603201,0.00003886607,0.000006168744],"category_scores_gemma":[0.0003341853,0.00008949882,0.00006994079,0.0001563325,0.00001301965,0.001482465,0.0002813414,0.000114715,7.352558e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004043738,"about_ca_system_score_gemma":0.0002167672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001657775,"about_ca_topic_score_gemma":0.000005930261,"domain_scores_codex":[0.9989741,0.00001918077,0.0003553409,0.000208346,0.0003213195,0.0001217225],"domain_scores_gemma":[0.9982042,0.0002382887,0.0003499842,0.0001354006,0.001020082,0.00005202716],"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":[0.0004376488,0.0004328874,0.02591908,0.0008656999,0.0006479897,0.00003599752,0.003875599,0.2845565,0.003368367,0.006520102,0.000273087,0.673067],"study_design_scores_gemma":[0.002763054,0.0005168794,0.00007837057,0.0009545679,0.00007731858,0.0003209862,0.0005314326,0.9132523,0.02566477,0.03378433,0.02133088,0.0007251273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01283032,0.0005442678,0.9859484,0.0002231243,0.0001001327,0.0001705102,0.000001401034,0.00004196479,0.0001398615],"genre_scores_gemma":[0.5416125,0.00003216976,0.4578527,0.0002972448,0.00006407387,0.000009189821,0.000002198232,0.000007617107,0.000122319],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6723419,"threshold_uncertainty_score":0.5455453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02535517324778782,"score_gpt":0.3171102658473063,"score_spread":0.2917550925995185,"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."}}