Alvaro Ortigosa

The impact of learning styles on student grouping for collaborative learning: a case study

Learning style models constitute a valuable tool for improving individual learning by the use of adaptation techniques based on them. In this paper, we present how the benefit of considering learning styles with adaptation purposes, as part of the user model, can be extended to the context of collaborative learning as a key feature for group formation. We explore the effects that the combination of students with different learning styles in specific groups may have in the final results of the tasks accomplished by them collaboratively. With this aim, a case study with 166 students of computer science has been carried out, from which conclusions are drawn. We also describe how an existing web-based system can take advantage of learning style information in order to form more productive groups. Our ongoing work concerning the automatic extraction of grouping rules starting from data about previous interactions within the system is also outlined. Finally, we present our challenges, related to the continuous improvement of collaboration by the use and dynamic modification of automatic grouping rules.

SmartBooks: a step beyond active-cookbooks to aid in framework instantiation

In this work we present SmartBooks, a new approach to support framework instantiation based on the active cookbook concept, extended with a combination of the concept of user-task modeling and least commitment planning methods. Based on this technique, a tool can present to the developer the different high level activities that can be carried on when creating a new application from a framework, taking as a basis the documentation provided by the designer through instantiation rules. For example, if the framework is in the accounting domain, some of the initial activities may be to create a new type of account, or to describe a new algorithm to calculate the tax rate. For each of these high level activities, there is a list of tasks that the user must carry out in order to complete the activity. When the user selects her next objective, the tool is able to build the sequence of tasks that have to be carried out to accomplish that objective; this list of tasks is called the instantiation plan, and the process of plan creation is named planning. In this paper we present the main characteristics of the planning approach and a example of the instantiation tool being developed.

Towards agent-oriented assistance for framework instantiation

In this work we present a tool for assisting object-oriented framework instantiation based on Intelligent Agent technology. Differently from other approaches, the user is able to select the functionality needed for the new application, and based on this selection an agent elaborates a sequence of programming activities that should be carried out in order to implement it. In addition, the agent guides the execution of the activities according to the framework design. To enable this behavior, the framework need to be documented following the SmartBooks method, which extends traditional framework documentation with instantiation rules. In this paper we present an example of an instantiation environment built based on these ideas and the main characteristics of the SmartBooks method for documenting frameworks through instantiation knowledge rules.

Extracting Emotions from Texts in E-Learning Environments

Affective and emotional factors seem to affect student motivation and, in general, the outcome of the learning process. By detecting and managing the emotions underlying a learning activity it would be possible to contribute to improve the student motivation and performance. In this work we explore different possibilities aimed at automatically extracting emotions from texts. We present a case study in which twelve essays written by a fresher student along her first semester in college are analyzed. Those results support the idea of using non-intrusive emotion detection for providing feedback to students. An example of use in an existing context-based adaptive e-learning system is presented. Incorporating emotions to this type of systems broadens their possibilities, allowing dynamic recommendation of activities according to the student emotions at each time, as well as emotion-based content adaptation, among others.

A data mining approach to guide students through the enrollment process based on academic performance

Student academic performance at universities is crucial for education management systems. Many actions and decisions are made based on it, specifically the enrollment process. During enrollment, students have to decide which courses to sign up for. This research presents the rationale behind the design of a recommender system to support the enrollment process using the students’ academic performance record. To build this system, the CRISP-DM methodology was applied to data from students of the Computer Science Department at University of Lima, Perú. One of the main contributions of this work is the use of two synthetic attributes to improve the relevance of the recommendations made. The first attribute estimates the inherent difficulty of a given course. The second attribute, named potential, is a measure of the competence of a student for a given course based on the grades obtained in related courses. Data was mined using C4.5, KNN (K-nearest neighbor), Naïve Bayes, Bagging and Boosting, and a set of experiments was developed in order to determine the best algorithm for this application domain. Results indicate that Bagging is the best method regarding predictive accuracy. Based on these results, the “Student Performance Recommender System” (SPRS) was developed, including a learning engine. SPRS was tested with a sample group of 39 students during the enrollment process. Results showed that the system had a very good performance under real-life conditions.

Dynamic Generation of Adaptive Web-Based Collaborative Courses

In this paper we present the use of adaptation techniques to dynamically generate adaptive collaborative Web-based courses. These courses are generated at runtime by selecting, at every step and for each student, the most suitable collaborative tasks to be proposed, the time at which they are presented, the specific problems to be solved, the most suitable partners to cooperate with and the collaborative tools to support the group cooperation. This selection is based on the users’ personal features, preferences, knowledge and behavior while interacting with the course. The advantages of this approach and the peculiarities of combining individual adaptation with collaboration seamlessly are also presented.

Inferring user personality in social networks: A case study in Facebook

In the context of adaptive intelligent systems, it is essential to build user models to be considered with adaptation purposes. Personality is an interesting user feature to be incorporated in user models; it may lead to know the user needs or preferences in different situations. In this direction, eliciting user personality is needed. This information should be obtained as unobtrusively as possible, yet without compromising the reliability of the model built. In this paper, we present a method for eliciting user personality by analyzing user interactions within the social network Facebook, with the goal of mining behavioral patterns. We have developed TP2010, a Facebook application based on the ZKPQ-50-cc questionnaire, to get information about both the user personality and his interactions within Facebook. We have built a classifier model starting from the analysis of a set of data from more than 11000 users. The results show that it is feasible to get information about the user personality by analyzing data from social network interactions.

A Rule-Based Formalism for Describing Collaborative Adaptive Courses

A significant number of collaborative and adaptive web-based systems have been created to support distance learning in the last years. However, there is a need of formalisms to support an extensible, flexible and maintainable specification of both collaboration and adaptation issues, especially when they are combined in an integrated environment. In this paper we present a rule-based formalism for the description of adaptive collaborative web-based courses, which are dynamically generated at runtime. The course elements, including the collaboration activities, are adapted to each student’s features, preferences, behaviors and achievements, at each time. The student’s actions while collaborating can also affect the later course adaptation. This formal representation provides some advantages regarding the desired features mentioned above.

Improving AEH courses through log analysis

This work has been partially funded by the Spanish Ministry of Science and Education through project HADA (TIN2007-64716). The first author is also funded by Fundacion Carolina.

Detecting and making use of emotions to enhance student motivation in e-learning environments

In this work, we investigate the possibility of detecting the student emotions by analysing their self-written essays. Detecting student emotions in e-learning environments would make it possible to enhance the learning processes accordingly. With that purpose, we have analysed 38 essays written by a student during her first three semesters in college. The results obtained support the idea that inferring user motivation from the emotions detected in texts is feasible. E-learning systems can use motivation information to propose activities aiming at increasing student engagement dynamically. In this direction, we present an example of use in an existing context-based adaptive e-learning system. Incorporating emotions to e-learning systems broadens their possibilities, allowing dynamic recommendation of activities and content adaptation according to student emotions. Finally, it makes it possible to detect potential problems within e-courses dynamically.