{"id":"W2165445075","doi":"10.5194/isprsarchives-xl-2-w1-143-2013","title":"IMPROVING VOLUNTEERED GEOGRAPHIC DATA QUALITY USING SEMANTIC SIMILARITY MEASUREMENTS","year":2013,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Geographic Information Systems Studies","field":"Social Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Volunteered geographic information; Computer science; Semantic similarity; Information retrieval; Data quality; Semantics (computer science); Profiling (computer programming); Context (archaeology); Linked data; Data mining; Completeness (order theory); Process (computing); Data science; Semantic Web; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.004632893,0.0004886445,0.0005763344,0.00119691,0.003654288,0.001545639,0.00317328,0.0001409286,0.00001773748],"category_scores_gemma":[0.002144516,0.0003255793,0.0003897779,0.001480852,0.005483445,0.001519608,0.002051912,0.0005270824,0.000006522245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007887022,"about_ca_system_score_gemma":0.0004365347,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.97998,"about_ca_topic_score_gemma":0.6017517,"domain_scores_codex":[0.992359,0.0007149829,0.002188383,0.0005246421,0.003426894,0.0007860396],"domain_scores_gemma":[0.9938902,0.001250883,0.002859025,0.0008825541,0.0008924245,0.0002248901],"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":[0.00006137024,0.00002190733,0.002832715,0.000070346,0.0001559185,1.207261e-7,0.008545077,0.000965593,0.001208773,0.00001428369,0.00006039152,0.9860635],"study_design_scores_gemma":[0.0006818488,0.00006141307,0.01158225,0.0003229942,0.00006664052,0.00004107313,0.01095399,0.9677869,0.0008031552,0.004191458,0.003133507,0.0003747487],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02778646,0.00005418663,0.9514922,0.005374147,0.002699449,0.001405026,0.000172845,0.00008156518,0.01093411],"genre_scores_gemma":[0.994979,0.0001457976,0.003447765,0.001074503,0.0001951802,7.396142e-7,0.00005751819,0.00001236566,0.00008713601],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9856887,"threshold_uncertainty_score":0.9999197,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06506388906274672,"score_gpt":0.3127034517741774,"score_spread":0.2476395627114306,"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."}}