{"id":"W4352981330","doi":"10.1109/iscmi56532.2022.10068466","title":"Empirical Evaluation of Word Representation Methods in the Context of Candidate-Job Recommender Systems","year":2022,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Durham College","funders":"","keywords":"Cosine similarity; Computer science; Ranking (information retrieval); Information retrieval; Similarity (geometry); tf–idf; Rank (graph theory); Recommender system; Context (archaeology); Matching (statistics); Set (abstract data type); Word (group theory); Artificial intelligence; Natural language processing; Term (time); Mathematics; Statistics; Pattern recognition (psychology)","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":[0.005932602,0.0000406151,0.0001168161,0.00008584582,0.00003778559,0.00001645943,0.0004524206,0.00001529136,0.00004555729],"category_scores_gemma":[0.0001159386,0.00002987931,0.00002785548,0.0003857668,0.000009910125,0.000107896,0.0001587826,0.00008786156,3.496278e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007408288,"about_ca_system_score_gemma":0.000080886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001685654,"about_ca_topic_score_gemma":0.00006448181,"domain_scores_codex":[0.9965258,0.0023288,0.0003460375,0.0001738879,0.0005476354,0.00007779294],"domain_scores_gemma":[0.9989491,0.0003832979,0.0001275169,0.0004320857,0.00009742576,0.0000105441],"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":[0.00003616658,0.0002536285,0.04903275,0.00005560386,0.00005940801,0.000002009133,0.05857955,0.1352913,0.002868254,0.06766084,0.005471797,0.6806887],"study_design_scores_gemma":[0.0003323769,0.00002778755,0.004981553,0.000003850098,0.000007572796,0.000003710901,0.005864205,0.9857492,0.000725684,0.001937358,0.0003265174,0.000040124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.144491,0.0001263297,0.8497407,0.001831028,0.0003532926,0.0003833218,0.000001137832,0.00001325069,0.003059882],"genre_scores_gemma":[0.968041,0.000001505368,0.03162542,0.0002005315,0.0000094081,0.0000732718,0.000001910338,0.000001877174,0.00004505111],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.850458,"threshold_uncertainty_score":0.2548215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2631662783351921,"score_gpt":0.4751181772925521,"score_spread":0.21195189895736,"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."}}