Knowledge Modelling for Ill-Defined Domains Using Learning Analytics: lineworkers Case
-
Guillermo Santamaría-Bonfil [3] [4] ; Héctor Daniel Díaz-Rodríguez [1] ; Gustavo Arroyo-Figueroa [4] ; Rafael Batres [2]
-
[1] Universidad de Colima
Universidad de Colima
México
-
[2] Instituto Tecnológico y de Estudios Superiores de Monterrey
Instituto Tecnológico y de Estudios Superiores de Monterrey
México
-
[3] CONACYT-INEEL (Cuernavaca, Morelos, Mexico)
-
[4] Instituto Nacional de Electricidad y Energías (Cuernavaca, Morelos, Mexico)
-
- Localización: The 11th International Conference on EUropean Transnational Educational: (ICEUTE 2020) / Álvaro Herrero Cosío (ed. lit.), Carlos Cambra Baseca (ed. lit.), Daniel Urda Muñoz (ed. lit.), Javier Sedano Franco (ed. lit.), Héctor Quintián Pardo (ed. lit.), Emilio Santiago Corchado Rodríguez (ed. lit.), 2021, ISBN 3-030-57798-8, págs. 409-418
- Idioma: inglés
- Texto completo no disponible (Saber más ...)
-
Resumen
Representation of knowledge used by E-learning systems to modulate learning processes plays a key role in its effectiveness. In ill-defined domains where training is carried out using an apprenticeship model such as the area of Technical and Vocational Education and Training, building a Knowledge Model is not straightforward. In such areas the knowledge model heavily depends on the journeyman tacit expertise which is spread across text documents such as manuals, books, reports, competency descriptions, among others. Hence, in this work it is proposed to employ Learning Analytics for building a Knowledge Model from text documents used in lineworkers vocational education. The model is organized by declarative, procedural, and competency layers. Each of these contains a semantic networked built from extracted concepts and the semantic relations between concepts is obtained using the Normalized Web Distance. Initial results shows that building knowledge models for ill-defined domains is promising, although more experimentation is required.
