Analysis of Student Achievement Scores via Cluster Analysis

  1. Jiménez Chaves, Viviana E. 1
  2. Miguel García-Torres 2
  3. David Becerra Alonso 3
  4. Francisco Gómez-Vela 2
  5. Federico Divina 2
  6. Vázquez-Noguera, José L. 1
  1. 1 Universidad Americana (Asunción, Paraguay)
  2. 2 Universidad Pablo de Olavide
    info

    Universidad Pablo de Olavide

    Sevilla, España

    ROR https://ror.org/02z749649

  3. 3 Universidad Loyola Andalucía
    info

    Universidad Loyola Andalucía

    Sevilla, España

    ROR https://ror.org/0075gfd51

Libro:
The 11th International Conference on EUropean Transnational Educational: (ICEUTE 2020)
  1. Álvaro Herrero (ed. lit.)
  2. Carlos Cambra (ed. lit.)
  3. Daniel Urda (ed. lit.)
  4. Javier Sedano (ed. lit.)
  5. Héctor Quintián (ed. lit.)
  6. Emilio Corchado (ed. lit.)

Editorial: Springer Suiza

ISBN: 3-030-57798-8 3-030-57799-6

Año de publicación: 2021

Páginas: 399-408

Congreso: International Conference on EUropean Transnational Educational (ICEUTE) (11. 2020. Burgos)

Tipo: Aportación congreso

Resumen

In education, the overall performance of every student is an important issue when assessing the quality of teaching. However, in the traditional educational system not all students have the same opportunity to develop their academic skills in an efficient way. Different teaching techniques have been proposed to adapt the learning process to the student profile. In this work, we analyze the profile of students according to their performance on academic activities and taking into account two different evaluation systems: work-based assessment and knowledge-based assessment. To this aim, data was collected during the fall semester of 2019 from a physics course at Universidad Loyola Andalucía, in Seville, Spain. In order to study the student profiles, a clustering approach combined with supervised feature selection was applied. Results suggest that two student profiles are clearly distinguished according to their performance in the course in both evaluation approaches. These two profiles correspond to students that pass and fail the course. The output of the analysis also indicates that there are redundant and/or irrelevant features. Therefore, machine learning techniques may be helpful for the design of effective activities to enhance the student learning process inthis physics course.