This complete work on innovative practices presents a proposal for inserting extension through actions in projects. The current university format in Brazil considers the in-dissociability between teaching, research, and extension. The first two are the most known dimensions, and extension constitutes an interdisciplinary, educational policy, cultural, scientific, and technological process, promoting the transforming interaction between the higher education institutions and society's other sectors, through the knowledge production and application, in permanent joint with research and teaching. In 2014, Brazil's Department of Education instituted the Education National Plan (in Portuguese, “Plano Nacional de Educação” (PNE)), which is still valid until 2023. One of its goals defines that at least 10% of the curricular credits for undergraduate courses must be integrated through extension programs or projects, prioritizing areas of great social relevance. At the same time, since 2019, Education National Conceil has instituted the new National Curricular Guidelines for the Engineering Undergraduate Courses, shifting the focus from the technical content to a new approach considering skills and competencies with the same importance for student education. Within this context, the challenge was to include extension activities, competencies, and skills in the curriculum of three undergraduate courses: Computing Engineering, Automation Engineering, and Information Systems. These courses are in an environment where the project culture is well-established, together with two graduate programs in the field of Computing. Moreover, most of these are research projects, where some activities can be characterized as extension. Also, professors of these courses are involved in specific extension projects. Considering all this context, the innovative practice proposed was to propose a curriculum framework for our undergraduate courses including project activities in the formal curriculum of students, taking place from 10% of traditional classroom training, in a curricular space-time where it is possible to work skills and competencies within real-life problems. In fact, some students experience this project environment but without any curricular formalization. In an empirical analysis of our former students, it is consensual that students who experience projects have a better education than those who only have a traditional classroom environment. The expected result is a curriculum that democratizes all the education spaces in the courses, including components in addition to those already worked in the traditional classroom. Also, it expected the extension as an educational process defined and carried out based on the reality requirements, in a way that university extension be part of the solution to the Brasil social problems.

This paper presents a programming exercise recommender system based on the Student’s Multiple Abilities and Skills (SMAS) model, which is developed from Item Response Theory and Elo System Classification, for estimation of multiple student’s abilities. This model assumes that programming exercises have many ways to be solved (paths) and each path requires different abilities from the student. To evaluate the recommender system, an experiment was conducted in a class of Algorithms and Data Structures I. For this study case, the recommender was connected to an Online Judge system that had a programming problem base. The results show that the proposed recommender has the ability to indicate relevant problems according to the student’s abilities.

This article presents a multi-skills estimation model for students using Online Judge systems. It is understood that there is not only one way to solve programming problems; and, for each solution form, a skill set is needed for the solution to be successful. The proposed model is based on performance expectations and integrates the Elo model, to estimate student’s abilities and problems, to the Multidimensional Item Response Theory model, which estimates the probability of success for each solution path. To validate the proposed model, a case study was carried out with students from the computing area, who solved problems on the beecrowd Online Judge platform. The proposed model was applied to the generated database. According to these results, it is observed that, in cases where the students got the solution right, more than 60% of the paths chosen by students are in accordance with paths indicated by the proposed model.

This Research to Practice Full Paper presents a proposed model to estimate the multiple skills of students in massive online environments that provide programming exercises, whose assessment methods occur automatically without human intervention. The proposed model is based on the M-ERS model and incorporates, from the TrueSkill model, the uncertainty regarding the student's skills. To validate the model, a database from the URI Online Judge platform was used and the M-ERS and TriMElo models were applied to compare the performance and behavior of the two models. The empirical results show that the proposed model updates student's skills more smoothly, according to the correctness or error of the exercise, according to the uncertainty of the skills.

In this full paper, research to practice, we present a classroom experience, in which we apply a teaching personalization model in an introductory computer science class. Students in this discipline are freshmen at the university and have different backgrounds related to solving programming problems. The traditional approach is standardized, tending to not serve each student in the best way and that is why we have adopted this group as a case study. We use the ELO-based model to recommend specific learning objects for each student, in order to match the student's ability with the difficulty of the problem. The learning objects correspond to programming problems in an online platform for automatic submission and evaluation. The experiment was divided into three stages. In the first, the student was able to freely choose problems from the platform repository. In the second stage, problems were randomly recommended (as a control). In the third stage, the recommendation was made using the model adopted. Students were encouraged to give feedback on their experience described in a free text and in the labeling of hashtags about the learning object. In addition, the rates of success, error, withdrawal and the frequency of access to the online platform were also collected. We observed that the students had a higher engagement (in terms of a higher frequency of use, a higher hit rate, and the production of positive feedbacks) at the stage when the recommendation matched the proposed model.

This complete article, from the research to practice category, presents an experiment carried out combining two models used to evaluate student skills, ELO Multidimensional and M-ERS. The objective of this experiment is to estimate and map the history of their multiple skills, in that way it was carried out incorporating the characteristic of the Multidimensional ELO - to track the history of multiple skills, and M-ERS - to estimating multiple skills that can be compensatory. To validate the experiment, we used a database composed of user submissions from an Online Judge platform from Brazil. Through the experiment results obtained, we concluded that for online programming problems platforms, the combination of both models proved to be satisfactory, through it was possible to map and observe the evolution of student's multiple skills.

In this work in progress we present an experiment to evaluate our learning object recommendation model. In the experiment, we propose the construction of a bot chat as interface of the recommendation system. The system will recommend programming problems to a group of students based on their behaviors in an online platform of programming problems. The students' development and their motivation to participate will be analyzed to verify the accuracy of our model.

This research-to-practice full paper proposals a metric of multiple skills for learning of programming students. This kind of system often need to diagnose the student's skill level. In the same way it needs to know the level of difficulty learning objects in its database. Such information makes it possible to make an appropriate match between student and the learning object. To model such tasks, we have adapted the ELO technique to apply a matchmaking process similar to that used in choosing opponents in chess tournaments or online matches. We used as a case study a virtual learning environment which has a repository with programming problems and the users interaction log. In this work we propose an extension to the traditional ELO model. In the classical model, ELO is a scalar value for each student and for each learning object. The extended model considers ELO as a multidimensional quantity, where each dimension is a skill in solving programming problems. The enumeration of the skills was made using the literature as well as statistical data of relevance of the attributes. The results are presented in this work.

Recommendation systems use computational techniques to select items in a personalized way to users, taking into account criteria such as history and interest. However, several authors point out that the process of recommendation in education requires models beyond the user's taste, in order to catalyze students' learning. In addition, feedback involves the student's experience. In this work we present a recommendation system of learning objects supported by a cognitive pedagogical model. The central idea of the system is to find an object that adequately challenges the student without bothering with similar problems or becoming discouraged when faced with problems beyond his or her ability. We integrate learning models into game models to integrate them into learning models. We used as a case study a virtual learning environment which has a repository with programming problems. The results indicate that, in general, when students choose more appropriate problems (ELOs similar to theirs), they get a greater number of correct answers in their submissions. When the student choose problems that do not seem to be challenging, in general, they make wrong submissions or give up learning on the platform.