Formally Modeling Learning Styles in Medical Intelligent Tutoring Systems
|
If you are the presenter of this abstract (or if you cite this abstract in a talk or on a poster), please show the QR code in your slide or poster (QR code contains this URL). |
Abstract
Background: The new educational paradigm is focused on the students and in their learning outcomes. Most e-learning platforms are simple repositories of content, based on the classroom paradigm, but not supporting the student’s learning needs and styles. Intelligent Tutoring Systems (ITSs) combined with Web 3.0 techniques (i.e. ontologies, intelligent agents, Bayesian networks) support personalized learning. In ITSs, the identification of the best learning styles is considered an essential element for succeeding in the teaching process. The use of questionnaires for identifying the student´s learning styles is an alternative; however, questionnaires are unreliable because students aren’t always sure how to answer the questions or they answer without thinking consciousness. Moreover the student can also be located in unfavorable environments (i.e. noisy) or emotional situation.
Objective: Considering the aforementioned problems, and specially the importance of learning styles in the teaching process, this article proposes a Bayesian Model to identify, in a semi-automatic way, the learning styles of Medical students using a Medical ITS.
Methods: ITSs are adaptive systems which use intelligence technologies to provide personalized learning according to individual student’s characteristics. Bayesian Networks (BNs) are directed acyclic graphs with nodes and arcs; where nodes represent random variables and arcs represent probabilistic correlation between variables. Combining BNs and ITSs, it is possible to represent uncertain relationships among parameters and to model the relationships between the learning styles and factors determining them. BNs model the different aspects of student’s behavior while he/she works with the system. Therefore, it infers his/her learning styles according to the modeled behavior.
Results (Research in progress): The proposed Bayesian model is being evaluated in the context of a Web-based medical course at the Health Sciences Faculty at University of Cauca, Colombia. To evaluate the precision of the proposed approach, the student´s learning style - detected with the Bayesian Model - is compared against the learning style obtained from a questionnaire (manual approach). The questionnaire is based on the Chaea-Learning Styles questionnaire proposed by Honey&Alonso, which has been broadly used in the medical field. A first stage in the evaluation process has been already performed, identifying the students’ learning styles using the questionnaire. The evaluation was carried out with 22 medicine students. The results evidenced different students learning styles as: active, reflexive, theoretical and pragmatic. These styles are the basis for the selection of the teaching strategies during the course execution. The second stage will be the evaluation of the learning styles detected with the Bayesian model.
Conclusions (Research in progress): Student models in e-learning systems are a main component of adaptive systems. The accurate identification of learning styles contributes to the personalization of e-learning systems. BNs provide a powerful and versatile technique for the semi-automatic identification of learning styles in the medical field. It is expected that the comparative evaluation evidence that the proposed approach is appropriate for identifying all learning styles with high levels of precision. The medical ITS developed combines Web 3.0 techniques (i.e. ontologies, intelligent agents, Bayesian networks) supporting personalized learning and e-learning system adaptability.
Objective: Considering the aforementioned problems, and specially the importance of learning styles in the teaching process, this article proposes a Bayesian Model to identify, in a semi-automatic way, the learning styles of Medical students using a Medical ITS.
Methods: ITSs are adaptive systems which use intelligence technologies to provide personalized learning according to individual student’s characteristics. Bayesian Networks (BNs) are directed acyclic graphs with nodes and arcs; where nodes represent random variables and arcs represent probabilistic correlation between variables. Combining BNs and ITSs, it is possible to represent uncertain relationships among parameters and to model the relationships between the learning styles and factors determining them. BNs model the different aspects of student’s behavior while he/she works with the system. Therefore, it infers his/her learning styles according to the modeled behavior.
Results (Research in progress): The proposed Bayesian model is being evaluated in the context of a Web-based medical course at the Health Sciences Faculty at University of Cauca, Colombia. To evaluate the precision of the proposed approach, the student´s learning style - detected with the Bayesian Model - is compared against the learning style obtained from a questionnaire (manual approach). The questionnaire is based on the Chaea-Learning Styles questionnaire proposed by Honey&Alonso, which has been broadly used in the medical field. A first stage in the evaluation process has been already performed, identifying the students’ learning styles using the questionnaire. The evaluation was carried out with 22 medicine students. The results evidenced different students learning styles as: active, reflexive, theoretical and pragmatic. These styles are the basis for the selection of the teaching strategies during the course execution. The second stage will be the evaluation of the learning styles detected with the Bayesian model.
Conclusions (Research in progress): Student models in e-learning systems are a main component of adaptive systems. The accurate identification of learning styles contributes to the personalization of e-learning systems. BNs provide a powerful and versatile technique for the semi-automatic identification of learning styles in the medical field. It is expected that the comparative evaluation evidence that the proposed approach is appropriate for identifying all learning styles with high levels of precision. The medical ITS developed combines Web 3.0 techniques (i.e. ontologies, intelligent agents, Bayesian networks) supporting personalized learning and e-learning system adaptability.
Medicine 2.0® is happy to support and promote other conferences and workshops in this area. Contact us to produce, disseminate and promote your conference or workshop under this label and in this event series. In addition, we are always looking for hosts of future World Congresses. Medicine 2.0® is a registered trademark of JMIR Publications Inc., the leading academic ehealth publisher.
This work is licensed under a Creative Commons Attribution 3.0 License.