ABSTRACT
The use of text mining and supervised machine learning algorithms on biomedical databases has become increasingly common. However, a question remains: How much data must be annotated to create a suitable training set for a machine learning classifier? In prior research with active learning in medical text classification, we found evidence that not only sample size but also some of the intrinsic characteristics of the texts being analyzed-such as the size of the vocabulary and the length of a document-may also influence the resulting classifier's performance. This study is an attempt to create a regression model to predict performance based on sample size and other text features. While the model needs to be trained on existing datasets, we believe it is feasible to predict performance without obtaining annotations from new datasets once the model is built.
Subject(s)
Artificial Intelligence , Documentation/classification , Documentation/statistics & numerical data , Meaningful Use/statistics & numerical data , Natural Language Processing , Terminology as Topic , Vocabulary, Controlled , Data Curation/methods , Data Mining/statistics & numerical data , Pattern Recognition, Automated/methods , Pattern Recognition, Automated/statistics & numerical data , Sample SizeSubject(s)
Male , Female , Humans , Documentation/classification , Documentation/history , Documentation/methodsABSTRACT
El objetivo general de este documento es generar un proceso de diagnóstico participativo del manejo documental actual al interior de la Secretaria Nacional de Salud, para identificar las Areas críticas en los que se refiere a recepción, flujos, cursos de proceso, despacho, archivo y resguardo de la documentación, en relación a los flujos de comunicación interna y externa de la Institución en estudio
Subject(s)
Documentation/classification , Data CollectionABSTRACT
Se basa principalmente en las fuentes documentales de la Inter-EP (Interinstitucional de Educación Popular); CEBIAE (Centro Boliviano de Investigación y Acción Educativas); CEE (Comisión Episcopal de Educación); y CEDEPSA (Centro Documental de Educación Popular "San Andrés); todas ellas vinculadas a la naciente Red Documental de Educación Popular (REDEP)