This study explores the integration of Augmented Intelligence (AuI) in Intelligent Tutoring Systems (ITS) to address challenges in Artificial Intelligence in Education (AIED), including teacher involvement, AI reliability, and resource accessibility. We present MathAIde, an ITS that uses computer vision and AI to correct mathematics exercises from student work photos and provide feedback. The system was designed through a collaborative process involving brainstorming with teachers, high-fidelity prototyping, A/B testing, and a real-world case study. Findings emphasize the importance of a teacher-centered, user-driven approach, where AI suggests remediation alternatives while teachers retain decision-making. Results highlight efficiency, usability, and adoption potential in classroom contexts, particularly in resource-limited environments. The study contributes practical insights into designing ITSs that balance user needs and technological feasibility, while advancing AIED research by demonstrating the effectiveness of a mixed-methods, user-centered approach to implementing AuI in educational technologies.

Textual cohesion is an essential aspect of a formally written text, related to linguistic mechanisms that connect elements such as words, sentences, and paragraphs. Several studies have proposed approaches to estimate textual cohesion in essays automatically. There is limited research that aims to study the extent to which the use of machine learning approaches can predict the textual cohesion of essays written in different languages (not just English). This paper reports on the findings of a study that aimed to propose and evaluate approaches that automatically estimate the cohesion of essays in Portuguese and English. The study proposed regression-based models grounded in conventional feature-based machine learning methods and deep learning-based pre-trained language models. The study also examined the explainability of automated approaches to scrutinize their predictions. We analyzed two datasets composed of 4,570 (Portuguese) and 7,101 (English) essays. The results demonstrate that a deep learning-based model achieved the best performance on both datasets with a moderate Pearson correlation with human-rated cohesion scores. However, the explainability of the automatic cohesion estimations based on conventional machine learning models offered a stronger potential than that of the deep learning model.

Linking data by finding matching instances in different datasets requires considering many characteristics, such as structural heterogeneity, implicit knowledge, and URI (Uniform Resource Identifier)-oriented identification. The authors propose a context-independent approach to align Linked data through an alignment process based on the ontological model’s components and considering data’s multidimensionality. The researchers experimented with the proposed approach against two methods for aligning linked data in two datasets and evaluated precision, recall, and f-measure metrics. The authors also conducted a case study in a real scenario considering a Brazilian publication dataset on computers and education. This study’s results indicate that the proposed approach overcomes the other methods (regarding the precision, recall, and f-measure metrics), requiring less work when changing the dataset domain. This work’s main contributions include enabling real datasets to be semi-automatically linked, presenting an approach capable of calculating resource similarity.

Scripted Collaborative Learning (CL) promotes meaningful interactions among students. Unfortunately, in some situations, the use of scripts causes motivational problems which in turn may lead to negative learning outcomes. In the last years, gamification has emerged as a promising technique to motivate and engage students towards learning process. However, gamification requires personalization based on knowledge about game design, and their impact on the students' motivation and learning outcomes. To address these issues, we proposed the formalization of an ontology to support the gamification of CL scenarios in which the game elements are tailored for each situation. These CL scenarios are known as ont-gamified CL sessions, and this paper presents the results of one empirical study conducted to evaluate their effects on the participants' intrinsic motivation and learning outcomes. This study was carried out as quasi-experiment with 62 undergraduate Brazilian students who participated either in non-gamified or ont-gamified CL sessions. Findings indicate that the intrinsic motivation was better in ont-gamified CL sessions, and that there was no significant difference on learning outcomes. Based on these results, we concluded that our approach is likely to deal with motivational problems in scripted CL.

Teachers are increasingly demanding to be active users of gamified intelligent tutoring systems (ITS). To effectively help teachers to use such systems, it is needed to provide simple and usable solutions for them without requiring advanced technical skills. In this work, we propose an authoring solution to help teachers in the design of gamified ITS. We evaluate our solution using a controlled experiment varying some features of the authoring proposal (template or scratch) with respect to ten metrics in the context of teachers and lecturers in Brazil. The results of this experiment allowed us to state that (i) authoring gamified ITS by using template requires much less time than from scratch; and (ii) there is no difference in the use or not of template for authoring gamified ITS with regards to the other metrics (e.g, perceived ease of use and usability, complexity, etc), but teachers have a high acceptance for all these metrics. The results found are of great importance since they might help teachers to design gamified ITS in a few minutes.

Gamification has been widely employed in the educational domain over the past eight years when the term became a trend. However, the literature states that gamification still lacks formal definitions to support the design of gamified strategies. This paper aims to create a taxonomy for the game elements, based on gamification experts' opinions. After a brief review from existing work, we extract first the game elements from the current state of the art, and then evaluate them via a survey with 19 gamification and education experts. The resulting taxonomy taxonomy included the description of 21 game elements and their quantitative and qualitative evaluation by the experts. Overall, the proposed taxonomy was in general well accepted by most of the experts. They also suggested expanding it with the inclusion of Narrative and Storytelling game elements. Thus, the main contribution of this paper is proposing a new, confirmed taxonomy to standardise the terminology used to define the game elements as a mean to design and deploy gamification strategies in the educational domain.

This research applies educational recommendations based on the five official correction criteria for the ENEM result, to improve writing. We developed a tool that uses peer assessment techniques to recommend pedagogical tasks to students' groups resulting from the application of clustering technique on 2012 ENEM data. The validation of these recommendations was made in an experiment with three cycles, where students had to: (1) write an essay; (2) evaluate essays from their peers; (3) follow the pedagogical recommendations received. We found that the strategic model of recommendation used in this study, enabled a measurable gain in quality of textual production.

Persuasion profiling has been shown to be a promising method to personalize persuasive messages that can influence users. In the context of learning, persuade students towards following pedagogical tasks is an important role of teachers and intelligent educational environments. To accomplish persuasion, it is necessary to measure students' susceptibility to influence principles. Susceptibility to Persuasion Scale (STPS) is an instrument that can measure users' susceptibility to influence principles. Currently, STPS is validated only for the English language. Thus, this study presents the translation, cultural adaptation, and initial validation of the Brazilian Portuguese version of the STPS questionnaire. We probed into the validity and reliability of the resulting questionnaire with 582 participants. Our results indicate that the final version of our questionnaire, which contains 19-items and 6-components, has a reasonable internal consistence (Cronbach's alpha = 0.78) and can adequately identify which influence principles have more impact on user' decisions.

Intelligent Tutoring Systems (ITSs) for Math still use traditional methods of input, such as computer keyboard and mouse. This strategy exposes students to a high extraneous cognitive load, due to the way the students are used to work, what could impair their learning. This paper presents a tool for Math ITSs that uses the student handwriting as data input. This tool was integrated into PAT2Math, an algebraic ITS, for an experimental evaluation in a public school with 48 students. It followed a design of control and experimental groups with pre and post-tests and a post questionnaire. Although our results have shown statistically significant improvement in student learning gains in both groups, no difference between groups was found. However, questionnaire responses suggest that handwriting provides a greater facility to the insertion of equations into ITSs for Math if compared with traditional methods (i.e., keyboard and mouse).

This project is inserted in the research and practice areas that support the development of educational resources, such as, serious games and training simulation, to understand how they should be planned, developed, evaluated, validated and used for the learning and assessment purposes. In this study, we have proposed and specified an agile, integrative and open method for educational resources development, named AIMED, in a holistic and multidisciplinary approach. This approach integrates the areas of simulation modeling, game design, instructional design, principles of agile development methods, project management practices and content domain. AIMED is based on integration of DevJSTA methodology, for creation of serious games, and AM-OER method, for development of open educational resources. A feasibility study was done with serious game development, which should be used and evaluated by domain experts, as well as, the methodology will be used and validated in new case studies.

The development and use of ontologies in creating more intelligent and effective applications have increased in recent years. This rise in popularity is due to the potential of ontologies in providing semantics for the data consumed by machines, allowing them to reason on these data. Providing sophisticated tools that improve the development of applications based on RDF and OWL can further accelerate the adoption of the Semantic Web. In this context, some types of ontology tools have been proposed, for instance, ontology editors, ontology reasoners, triple store tools, RDF frameworks and object triple mapping (OTM) systems. In particular, OTM systems (e.g., AliBaba, KOMMA, JOINT and so on) are of utmost importance for developing ontology-based applications through the object-oriented paradigm. They map RDF triples into data objects, enabling developers to handle RDF triples as objects in object-oriented applications. In a similar way, developers of relational database applications have been using object-relational mapping (ORM) systems, for example Hibernate, to map relational databases into objects as well as to manage the object states. The main object state that Hibernate provides is the detached one; however, except for Empire, current OTM systems do not provide detached objects. The great difference between these two types of objects is that the former one has its life cycle independent of the underlying database connection, while the latter one is bound to the connection. In this way, this paper presents an object triple mapping system that supports detached objects, named JOINT-Detached (JOINT-DE). By using JOINT-DE, developers of ontology-based applications can (i) use the objects coming from the triple store as objects of the business model, (ii) use such objects as data transfer objects (DTOs) between subsystems, and (iii) use of less resources (triple store connections) to load object properties. To evaluate the proposed tool, we first describe how we conducted an experiment to empirically compare our tool with another OTM widely used by the community. We measure performance and memory usage regarding create, retrieve and update operations. Our results indicate that: (1) JOINT-DE has better performance results in all three operations; (2) JOINT-DE has an advantage over AliBaba with respect to the memory usage in the retrieve operation; (3) AliBaba uses less memory than JOINT-DE in the update operation; and (4) we could not find statistically significant differences between the tools regarding memory usage in the create operation. Finally, to illustrate the benefits of the proposed system, a case study of a real application is presented, outlining the architectural limitations of the application using an existing OTM in the literature, as well as showing positive results to the use of JOINT-DE.

To reduce the complexity intrinsic to LD manipulation, software tools are used to publish or consume data associated to LD activities. However, few developers have a broad understanding of how software tools may be used in publication or consumption of Linked Data. The goal of this work is to investigate the use of software tools in Linked Data publication and consumption processes. More specifically, understanding how these software tools are related to process of publication or consumption of LD. In order to meet their goal, the authors conducted a Systematic Literature Review (SLR) to identify the studies on the use of software tools in these processes. The SLR gathered 6473 studies, of which only 80 studies remained for final analysis (1.25% of the original sample). The highlights of the study are: (1) initial steps of the publication process are fairly supported by the software tools; (2) Non-RDF serialization is fairly supported in publication and consumptions process by the software tools; and (3) there are non-supported steps in consumption and publication processes by the tools.

Infographic is a type of information visualization that uses graphic design to enhance human ability to identify patterns and trends. It is popularly used to support spread of information. Yet, there are few studies that investigate how infographics affect learning and how individual factors, such as learning styles and enjoyment of the information affect infographics perception. In this sense, this paper describes a case study performed in an online platform where 27 undergraduate students were randomly assigned to view infographics (n=14) and graphics+text (n=13) as learning materials about the same content. They also responded to questionnaires of enjoyment and learning styles. Our findings indicate that there is no correlation between learning styles and post-test scores. Furthermore, we did not find any difference regarding learning between students using graphics or infographics. Nevertheless, for learners using infographics, we found a significant and positive correlation between correct answers and the positive self-assessment of enjoyment/pleasure. We also identified that students who used infographics keep their acquired information longer than students who only used graphics+text, indicating that infographics can better support robust learning.

Some recent studies discussed the pros and cons of gender difference in the use of intelligent educational technologies. According to these studies, there is a difference in behavior, attitude, learning and emotion. However, most of the studies were conducted for Mathematics and in a well developed ecological setting. In this work, we investigated the Mars and Venus Effect, by measuring together different variables, such as learning performance (in Portuguese and Mathematics), age, location area, and learning technology. The study was a random pre/posttest control group experimental design, on which 191 students from public schools in Brazil participated. The experimental group used an adaptive learning technology (called MeuTutor) for nine months, while the control group did not use any educational technology during the study. The most relevant results are: i) the use of the adaptive learning technology improves student's performance in Mathematics and Portuguese for both male and female students, ii) the improvement of male student's performance is more significant, against female students, iii) when we focus on technology, male students had better performance in mathematics, but no significant difference in Portuguese.

This paper presents a dynamic Bayesian network model for the assessment of students' algebraic knowledge in step-based intelligent tutoring systems. The proposed work assesses knowledge about concept, skills, and misconceptions of learners. Furthermore, the proposed model is independent of the problems provided by the system (i.e., equations), because it considers the algebraic operation used by the student to solve a step as evidence instead of the final solution provided by the student. Results of evaluations comparing student's performance on a posttest with the inference of the proposed model showed statistically significant similarities between them, indicating that the inference performed by the model was accurate.

In the last decades, education has been supported by technology in order to reach more people and produce significant benefits to teaching and learning. Part of the success of technology and education is due to the capacity technology can adapt teaching and learning to different contexts. More recently, we noticed an increase in the use of game elements (gamification) in educational environments, which intends to promote students' engagement and, consequently, improve their learning experience. However, we do not know if the use of these elements brings the promised results. In this paper, we conducted an observational analysis focusing in XP (experience points) and Badges, checking their correlation with the students learning, in order to investigate the influence of these gamification elements.

Nowadays, with the spread of massive open online courses (MOOC) there is a significant increase in the number of students learning through the Web. Consequently, there is a growing concern about the quality of the Web-based Educational Software (WES). Despite of various mechanisms to evaluate the quality of this software, most of the quality criteria are spread in different articles found in the literature. Therefore, this work aims to conduct a Systematic Literature Mapping to identify the criteria to assess the quality of WES, and classify them according to their contribution. A total of 78 studies were analyzed and classified into four categories of quality: pedagogical, technical, organizational and social. The results contribute to support the maintenance and improvement of the quality of the WES available to the community.

Affective states such as personality trait, emotion and mood are critical elements that affect group learning. Nevertheless, few studies classify and analyze the research findings of the community to explicitly show the real impact and use of affective states in CSCL environments. Thus, this paper presents the development of a systematic mapping of the literature to answer three questions: (i) What are the affective states frequently used in CSCL environments? (ii) Were affective states in CSCL environment empirically evaluated? (iii) What are the types of environments that use affective states to support group learning? To answer these questions, seven digital libraries were queried and 31 studies were deeply analyzed. As main results, we verified that: (i) 54,84% of the studies deal with 'emotions' in CSCL environments, (ii) 51,61% of the studies were empirically evaluated, and (iii) LMS (38,71%) and E-Learning systems (22,58%) are the most common types of environments that use affective states to support collaborative learning. Finally, we also identified gaps and opportunities to conduct research on adaptive/intelligent CSCL systems to support better group formation and customization of group activities using affective states.

The interface is the main mechanism of communication between user and system features. In educational software, successful user interface designs minimize the cognitive load on users, thereby users can direct their efforts to maximize their understanding of the educational concepts being presented. We investigated whether a reduced interface make few cognitive demands on users in comparison to a complete interface. In this context, this research aims at analyzing a reduced and a complete interface of an interactive geometry software, and verify the educational benefits they provide. To this end, we designed the interfaces and carried out an experiment involving 69 undergraduate students. The experimental results indicate that an interface that hides advanced and extraneous features helps novice users to perform slightly better than novice users using a complete interface. After receiving proper training, however, a complete interface makes users more productive than a reduced interface.