M-Learning as a Driving Force of Social Engagement, Responsible Collaboration, and Student Interaction

The normalization of the use of these devices offers facilities for exploration, personalization of learning, and greater adaptation to the rhythm of students. In this chapter, a conceptualization of m-Learning will be presented including the main m-Learning features. After, the authors focus on applications for social sciences education. This chapter is divided into two parts. The authors review general applications that can be useful for the teaching and learning of social sciences, offering numerous procedural possibilities at the service of the area. After, they review some specific applications that, beyond concepts and facts, offer multiple procedural possibilities connected with conceptual contents of this area of knowledge. Finally, other resources and teaching guidance for m-Learning will be presented, including relevant websites with lots of resources for the teaching and learning of social sciences, geography, and history.

Proposal of Architecture And Application of Machine Learning (Ml) as A Strategy For The Reduction of University Desertion Levels Due to Academic Factors

Introduction: Machine Learning arises as one of the techniques of artificial intelligence, with the development of computer programs that, through algorithms, access data and use them to learn and predict results. Their application in education allows for the characterization of problems or difficulties in learning through the analysis of student performance. Objective: Identification of applications of Machine Learning that can be applied to the educational field accompanied by a proposal of architecture for the application in an environment of personalized education. Methodology: This article begins with the review of the literature on the characteristics of Machine Learning and academic desertion, with an emphasis on the Colombian case, the Hyper-personalization and its applicability to learning methodologies. Then, a proposal of architecture in a Machine Learning environment is generated in order to mitigate the academic desertion caused by academic factors. Finally, we propose mechanisms for evaluating the proposed architecture, with a subsequent synthesis and discussion of the results. Conclusions: The construction of a Moodle architecture for the hyper-personalization of learning, is a global perspective of the representative factors proposed for the development of applications through Machine Learning. This could lead to a decrease in levels of university academic desertion because it facilitates the management of knowledge, information and adaptation through the analysis of scenarios. Originality: The proposed architecture is shown as an application of machine learning in social cases such as academic desertion, allowing the inclusion of automatic learning models with the requirements of an educational environment. Restrictions: The case for the application for the Hyper-personalization of learning uses an academic approach which can generate invalid results regarding desertion levels.