Publicación: SIAMES. Social Impact Advisor and Measurement System
Cargando...
Fecha
2020-10-01
Autores
Editor/a
Director/a
Tutor/a
Coordinador/a
Prologuista
Revisor/a
Ilustrador/a
Derechos de acceso
Atribución-NoComercial-SinDerivadas 4.0 Internacional
info:eu-repo/semantics/openAccess
info:eu-repo/semantics/openAccess
Título de la revista
ISSN de la revista
Título del volumen
Editor
Universidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Inteligencia Artificial
Resumen
Actualmente existe una tendencia que recupera los enfoques más tradicionales de la IA e investiga sobre su combinación con otras técnicas ligadas a la Ciencia de Datos, generando una simbiosis entre métodos simbólicos y probabilistas que ha despertado el interés de investigadores y profesionales de la IA. Mediante esta investigación profundizamos en este campo planteando y estudiando un sistema RBC combinado con minería de textos, aplicando de manera novedosa un enfoque ontológico en ambas tareas, todo ello aplicado a la medición de impacto social. En concreto, de_nimos un modelo de sistema RBC, proponemos una ontología para el campo de conocimiento de la medición de impacto social y funciones de similitud semántica originales para la recuperación de casos. En este artículo reportamos los resultados de nuestra experimentación con SIAMES (Social Impact Advisor and Measurement System), un sistema recomendador de indicadores de impacto social. El sistema cuenta con dos fases: en primer lugar, extrae información estructurada de un corpus de informes de medición de impacto mediante Minería de Textos Semántica basada en ontologías. En segundo lugar, inspirándonos en el Razonamiento Basado en Casos, recupera los indicadores más adecuados para cada empresa social.
Currently there is a trend that recovers the more traditional approaches to AI and investigates its combination with other techniques linked to Data Science, generating a symbiosis between symbolic and probabilistic methods that has aroused the interest of researchers and AI professionals. Through this research we delve into this _eld by proposing and studying a CBR system combined with text mining, applying an ontological approach in both tasks in a novel way, all applied to the measurement of social impact. Specifically, we de_ne a RBC system model, we propose an ontology for the _eld of knowledge of social impact measurement and original semantic similarity functions for the recovery of cases. In this article we report the results of our experimentation with SIAMES (Social Impact Advisor and Measurement System), a recommender system of social impact indicators. The system has two phases: _rst, it extracts structured information from a corpus of impact measurement reports using Semantic Text Mining based on ontologies. Second, taking inspiration from Case-Based Reasoning, it retrieves the most appropriate indicators for each social enterprise.
Currently there is a trend that recovers the more traditional approaches to AI and investigates its combination with other techniques linked to Data Science, generating a symbiosis between symbolic and probabilistic methods that has aroused the interest of researchers and AI professionals. Through this research we delve into this _eld by proposing and studying a CBR system combined with text mining, applying an ontological approach in both tasks in a novel way, all applied to the measurement of social impact. Specifically, we de_ne a RBC system model, we propose an ontology for the _eld of knowledge of social impact measurement and original semantic similarity functions for the recovery of cases. In this article we report the results of our experimentation with SIAMES (Social Impact Advisor and Measurement System), a recommender system of social impact indicators. The system has two phases: _rst, it extracts structured information from a corpus of impact measurement reports using Semantic Text Mining based on ontologies. Second, taking inspiration from Case-Based Reasoning, it retrieves the most appropriate indicators for each social enterprise.
Descripción
Categorías UNESCO
Palabras clave
Citación
Centro
Facultades y escuelas::E.T.S. de Ingeniería Informática
Departamento
Inteligencia Artificial