Automatic personality recognition has become relevant due to the advancement of artificial intelligence and the widespread use of mobile devices. This study proposes predicting personality traits according to the OCEAN model by integrating mobile sensor data and self-reports using deep neural networks. Through a mobile application, sensor data and daily surveys related to device usage were collected. Four model architectures (MLP, CNN, LSTM and Transformer) were evaluated, finding that CNN is most effective with raw data, while the Transformer excels at including temporal and frequential attributes. These results represent a breakthrough in customized and empathic technologies in mobile data-based personality recognition.

Programming skills are central to technological innovation, and intelligent learning environments are essential for acquiring them effectively. We present Javalí Notebook, a web-based interactive literate programming environment seamlessly integrated with a learning management system, designed to enhance the teaching and learning of programming. The platform allows students to engage with courses by exploring example notebooks, completing unit tests and other assessments, and incrementally developing their own programs with real-time compiler feedback and debugging support. Additionally, Javalí Notebook can serve as a classroom code presentation tool, enhancing live demonstrations and collaborative learning. The system was evaluated using the Technology Acceptance Model (TAM), and results showed positive student perceptions and intentions toward its use.

This paper introduces COVIA (Code + Video + AI), a constructive Video-Based Learning (VBL) platform aiming to address ongoing challenges in computer science education, particularly those related to student engagement and instructor workload. The system was deployed in a blended learning setting as supplementary instruction in mandatory introductory programming courses at a university in Mexico. Curriculum materials and videos were designed using a human-in-the-loop workflow assisted by Generative AI (GenAI) and validated by subject-matter experts. This study employs a longitudinal, quasi-experimental quantitative design, complemented by a quantitative acceptance assessment based on the Technology Acceptance Model (TAM). The evaluation focused on three distinct phases of the introductory Java curriculum: (1) Language Elements, (2) Selective Structures, and (3) Iterative Structures. Statistical analysis using the Wilcoxon Signed-Rank test confirmed that the Experimental Group achieved highly significant learning gains across all three phases (p<0.001). In contrast, the Control Group failed to achieve statistically significant growth in Phase 1 (p=0.119) and Phase 3 (p=0.448). In conclusion, the results suggest that the COVIA platform supports the development of introductory programming competencies as a supportive tool within a blended instructional framework.

This paper presents SmartMathAI, an educational tool designed to support students in learning mathematics. The educational tool is based on Problem-Based Learning (PBL) with a personalized virtual tutor developed with a large language model (LLM). The virtual tutor guides the student through the problem-solving process, answers questions, and evaluates their reasoning. The use of the tool aids in mathematics learning by offering a personalized alternative that adapts to the student’s needs. SmartMathAI was evaluated with middle school students, obtaining favorable results both for learning and for student motivation when using the technology, allowing students to learn more autonomously and at their own pace.

A new era of challenges and opportunities in education has emerged with the development of Large Language Models (LLMs). Along with these, educational content generation tools using LLMs have been created, making the task of creating courses in different fields of knowledge easy and efficient. However, the integration of XR technologies into these models remains a challenge. This paper describes the creation of an educational platform powered by LLM that allows teachers to generate personalized resources on any subject, with or without XR scenarios, and then modify and distribute these contents to students. Lesson preparation, grading, and producing instructional materials are among the duties that the platform automates. University students have been used to test the LLM tool. The evaluations' outcomes and the items that were produced are promising.

The growth of social networks as mass media has enabled faster and closer interaction between users, but it also presents challenges, such as the risk of spreading hate speech. Early detection of such harmful posts is critical. This article presents a methodology to create a unique corpus of Spanish-language comments collected from MisProfesores.com platform, covering all states in Mexico. This process resulted in a dataset of 18,000 unlabeled samples and 853 manually labeled samples. In addition to describing the corpus construction process, the results of the evaluation of different models trained with these data are presented, as well as their comparison with previous works for toxicity detection, highlighting the relevance of the Spanish corpus development for specific tasks. As a result, our Transformer-based model performed better than the state-of-the-art models in the binary toxicity classification, reaching a value of 0.9649 in accuracy and 0.9645 in F1 score.

This book chapter introduces an LLM-powered educational tool for building science learning environments using a fully cloud-based platform. The tool is an educational platform driven by LLM that attempts to save teachers time by automatized processes like lesson planning, grading, and resource generation. Using this platform, educators can modify and update pre-existing materials to fit the needs of any reader, produce unique science-related resources, and edit and distribute these materials to students. Any student can access instructional materials generated with the authoring tool interface through an internet-connected device. The tool accomplishes this by combining several technologies, including frameworks and tools like Ollama, JavaScript, and open-source LLMs like LLaMA 3, DeepSeek, Qwen2, and Gemma 2.

This article presents the development and evaluation of XploRe, an Extended Reality tool designed to enhance the learning experience of secondary school students, specifically focusing on the Solar System and its associated physical phenomena. XploRe integrates WebXR technology, ensuring broad compatibility across various devices such as PCs and mobile platforms, and supports multiple viewing modes, including Web, Augmented Reality (AR), and Virtual Reality (VR). To assess the effectiveness of XploRe, a series of controlled experiments were conducted with secondary school students. The evaluation process included a pre-test to evaluate students' knowledge about the topics, interaction with the experiments within XploRe, and subsequent post-tests to measure learning outcomes.

This study investigates the potential of Multimodal Large Language Models to evaluate the quality of Unified Modelling Language (UML) class diagrams, with a focus on their ability to assess class structures and attribute information in alignment with object-oriented design principles. Thirty-four engineering students completed a design task involving the application of five object-oriented design principles known collectively as the S.O.L.I.D. principles (Single Responsibility, Open/Closed, Liskov Substitution, Interface Segregation, and Dependency Inversion). Their solutions were independently assessed by three expert instructors and four Multimodal Large Language Models: ChatGPTChatGPT-4, Gemini, Amazon AI, and Claude 3.5 Sonnet. Quantitative analysis compared AI-generated scores to instructor consensus ratings using inter-rater reliability metrics, while a grounded theory approach was used to qualitatively identify and classify AI evaluation errors. Results indicate that while MLLMs demonstrate promising partial scoring alignment with experts, they consistently exhibit significant limitations in semantic interpretation and evaluative reasoning, often leading to inconsistencies. These findings highlight that despite their potential, MLLMs are not yet reliable replacements for human expertise and underscore the critical need for improved model alignment with domain-specific assessment practices. They also suggest future directions for carefully integrated hybrid instructor-AI evaluation workflows in educational settings.

Different areas of education have undergone a significant transformation due to the rapid progress of extended reality in recent years. Nonetheless, existing eXtended Reality (XR) authoring tools often require advanced programming skills, limiting their accessibility to educators and students. To address this challenge, we introduce BabloXR, an intuitive authoring tool that leverages Blockly to enable visual, code-free programming for creating educational XR environments. BabloXR was evaluated through a user study involving teachers and students who successfully designed their own XR learning environments. The results indicate that users of BabloXR were able to create complete and detailed scenarios, with usability testing revealing high ease of use, positive user experience, and strong interest in extended reality.

In recent years, along with advances in affective computing, automatic personality recognition has become an emerging area of research. However, the problem of correct personality recognition remains challenging. In this paper, the problem of automatic personality recognition is supported with the use of Generative Artificial Intelligence and specifically with the use of large language models, also known as LLMs. It is based on an existing personality recognition corpus in text, built with the support of traditional personality questionnaire techniques and text extracted from the audio of videos. Then, with the support of Generative AI, augmented and balanced versions of the same corpus were created for each personality trait. The obtained corpora were used to train and optimize different automatic and deep learning models. The results obtained with different classification models on these corpora show higher values in the accuracy and precision metrics compared to those obtained in the baseline study.

Personality encompasses a range of traits that define individual emotions, behaviors, and patterns of interaction. Given that these behavioral patterns likely influence how people engage with mobile devices, which are deeply integrated into daily life, this study explores the feasibility of assessing personality attributes through data collected from mobile sensors, specifically accelerometers. We present the methodology for data acquisition and preprocessing, along with the implementation of artificial neural networks and a multilayer perceptron for automatic personality prediction. Preliminary results indicate promising potential for inferring personality traits based on mobile usage data, highlighting accelerometer-derived features as valuable predictors in the absence of traditional surveys.

Appears in: INTED2024 Proceedings Publication year: 2024Pages: 6495-6504ISBN: 978-84-09-59215-9ISSN: 2340-1079doi: 10.21125/inted.2024.1700Conference name: 18th International Technology, Education and Development ConferenceDates: 4-6 March, 2024Location: Valencia, Spain

The creation of extended reality applications, which combine elements of virtual reality, augmented reality and mixed reality, is complex and demanding, especially in education where its use has grown exponentially in recent years. This paper presents the development of an authoring tool that allows the creation of extended reality environments in the field of education, so that teachers without programming experience can create and share extended reality environments in an intuitive and efficient way. The authoring tool has been tested with university students. The results of the evaluations and products generated are promising.