{"id":"W2343814825","doi":"10.1109/tla.2016.7459622","title":"Automatic algorithm to classify and locate research papers using natural language","year":2016,"lang":"en","type":"article","venue":"IEEE Latin America Transactions","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Data mining; Upload; Natural language; Set (abstract data type); Statistical classification; Artificial intelligence; Knowledge base; Algorithm; Information retrieval; Machine learning; World Wide Web","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.002790371,0.001008702,0.001084715,0.01337694,0.001196972,0.00370772,0.00219559,0.00136636,0.003889703],"category_scores_gemma":[0.01072589,0.0004066876,0.001472393,0.006157146,0.0006393669,0.002946898,0.001633049,0.001028427,0.003900195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001284747,"about_ca_system_score_gemma":0.004189288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003788434,"about_ca_topic_score_gemma":0.005087553,"domain_scores_codex":[0.9966921,0.0005455152,0.0005728891,0.0009036962,0.00113808,0.0001476514],"domain_scores_gemma":[0.9935695,0.002563749,0.0008485713,0.0005377033,0.002316276,0.0001642668],"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":[0.0003023898,0.0004425002,0.007141802,0.001168051,0.0001500889,0.0004693216,0.0007868193,0.005010733,0.03475684,0.0163334,0.01902707,0.9144111],"study_design_scores_gemma":[0.0003329398,0.0005913196,0.01526026,0.0007099545,0.0004819017,0.003999142,0.002495901,0.5827035,0.118812,0.0891564,0.1851396,0.0003170807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01594892,0.0006373567,0.9656282,0.0006074142,0.0001069036,0.0007950072,0.002966229,0.009942914,0.003367075],"genre_scores_gemma":[0.03395757,0.0001726151,0.9597847,0.0001482545,0.00003800047,0.0004284942,0.003782477,0.0001223517,0.001565463],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.986623,"threshold_uncertainty_score":0.0147571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04327746162101873,"score_gpt":0.3328154659512365,"score_spread":0.2895380043302178,"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."}}