{"id":"W2344430697","doi":"10.3233/web-160335","title":"Accurate and efficient query clustering via top ranked search results","year":2016,"lang":"en","type":"article","venue":"Web Intelligence","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"National Science Foundation","keywords":"Computer science; Cluster analysis; Data mining; Information retrieval; DBSCAN; Search engine; Web search query; Metric (unit); Feature (linguistics); Hierarchical clustering; Similarity (geometry); Query expansion; Fuzzy clustering; CURE data clustering algorithm; Machine learning; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.002318833,0.00182566,0.002771639,0.007601652,0.001896532,0.004015681,0.002908799,0.001643309,0.001547221],"category_scores_gemma":[0.01533982,0.000707758,0.001197927,0.008199519,0.0006852128,0.003659495,0.001967589,0.001101629,0.002630474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00179762,"about_ca_system_score_gemma":0.003298161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01545779,"about_ca_topic_score_gemma":0.01830443,"domain_scores_codex":[0.9944939,0.001182337,0.0004718932,0.0009158106,0.002489722,0.0004463088],"domain_scores_gemma":[0.9934662,0.001456364,0.0006072649,0.002139432,0.002102433,0.0002283215],"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":[0.001240867,0.0009052553,0.01144361,0.0006042672,0.0004269657,0.0002676218,0.0009449946,0.1400104,0.04741715,0.01444044,0.01993027,0.7623681],"study_design_scores_gemma":[0.00007141317,0.000197886,0.003988991,0.00003012104,0.0001072822,0.0005008262,0.0005864009,0.9454324,0.03099063,0.01330144,0.004686869,0.0001058418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08412556,0.001804109,0.9000657,0.0003946711,0.0001041203,0.00050919,0.001154976,0.007722177,0.004119539],"genre_scores_gemma":[0.4091545,0.0005371788,0.583985,0.0001157242,0.0001065502,0.000174346,0.003086315,0.0003656743,0.002474671],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01545779,"threshold_uncertainty_score":0.03073561,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03174857622042965,"score_gpt":0.2767855005657308,"score_spread":0.2450369243453011,"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."}}