An Ambient Intelligence responds to user requests based on several contexts. A relevant context is related to what has happened in the ambient; therefore, it focuses a primordial interest on events. These involve information about time, space, or people, which is significant for modeling the context. In this paper, we propose an event-driven approach for context representation based on an ontological model. This approach is extendable and adaptable for academic domains. Moreover, the ontological model to be proposed is used in reasoning and enrichment processes with the context event information. Our event-driven approach considers five contexts as a modular perspective in the model: Person, temporal (time), physical space (location), network (resources to acquire data from the ambient), and academic events. We carried out an evaluation process for the approach based on an ontological model focused on (a) the extensibility and adaptability of use case scenarios for events in an academic environment, (b) the level of reasoning by using competence questions related to events, (c) and the consistency and coherence in the proposed model. The evaluation process shows promising results for our event-driven approach for context representation based on the ontological model.

Semantic relationships between words provide relevant information about the whole idea in the texts. Existing embedding representation models characterize each word as a vector of numbers with a fixed length. These models have been used in tasks involving text classification, such as recommendation and question–answer systems. However, the embedded information provided by semantic relationships has been neglected. Therefore, this paper proposes an approach that involves semantic relationships in embedding models for text classification, which is evaluated. Three embedding models based on semantic relations extracted from Wikipedia are presented and compared with existing word-based models. Our approach considers the following relationships: synonymy, hyponymy, and hyperonymy. They were considered since previous experiments have shown that they provide semantic knowledge. The relationships are extracted from Wikipedia using lexical-syntactic patterns identified in the literature. The extracted relationships are embedded as a vector: synonymy, hyponymy–hyperonymy, and a combination of all relationships. A Convolutional Neural Network using semantic relationship embeddings was trained for text classification. An evaluation was carried out for the proposed relationship embedding configurations and existing word-based models to compare them based on two corpora. The results were obtained with the metrics of precision, accuracy, recall, and $F_1$-measure. The best results for the 20-Newsgroup corpus were obtained with the hyponymy–hyperonymy embeddings, achieving an accuracy of 0.79. For the Reuters corpus, $F_1$-measure and recall of 0.87 were obtained using synonymy–hyponymy–hyperonymy.

Topic discovery involves identifying the main ideas within large volumes of textual data. It indicates recurring topics in documents, providing an overview of the text. Current topic discovery models receive the text, with or without pre-processing, including stop word removal, text cleaning, and normalization (lowercase conversion). A topic discovery process that receives general domain text with or without processing generates general topics. General topics do not offer detailed overviews of the input text, and manual text categorization is tedious and time-consuming. Extracting topics from text with an automatic classification task is necessary to generate specific topics enriched with top words that maintain semantic relationships among them. Therefore, this paper presents an approach that integrates text classification for topic discovery from large amounts of English textual data, such as 20-Newsgroups and Reuters Corpora. We rely on integrating automatic text classification before the topic discovery process to obtain specific topics for each class with relevant semantic relationships between top words. Text classification performs a word analysis that makes up a document to decide what class or category to identify; then, the proposed integration provides latent and specific topics depicted by top words with high coherence from each obtained class. Text classification accomplishes this with a convolutional neural network (CNN), incorporating an embedding model based on semantic relationships. Topic discovery over categorized text is realized with latent Dirichlet analysis (LDA), probabilistic latent semantic analysis (PLSA), and latent semantic analysis (LSA) algorithms. An evaluation process for topic discovery over categorized text was performed based on the normalized topic coherence metric. The 20-Newsgroups corpus was classified, and twenty topics with the ten top words were identified for each class. The normalized topic coherence obtained was 0.1723 with LDA, 0.1622 with LSA, and 0.1716 with PLSA. The Reuters Corpus was also classified, and twenty and fifty topics were identified. A normalized topic coherence of 0.1441 was achieved when applying the LDA algorithm, obtaining 20 topics for each class; with LSA, the coherence was 0.1360, and with PLSA, it was 0.1436.

The increasing volume of medical information available in digital format presents a significant challenge for researchers seeking to extract relevant information. Manually analyzing voluminous data is a time-consuming process that constrains researchers’ productivity. In this context, innovative and intelligent computational approaches to information search, such as large language models (LLMs), offer a promising solution. LLMs understand natural language questions and respond accurately to complex queries, even in the specialized domain of medicine. This paper presents MédicoBERT, a medical language model in Spanish developed by adapting a general domain language model (BERT) to medical terminology and vocabulary related to diseases, treatments, symptoms, and medications. The model was pre-trained with 3 M medical texts containing 1.1 B words. Furthermore, with promising results, MédicoBERT was adapted and evaluated to answer medical questions in Spanish. The question-answering (QA) task was fine-tuned using a Spanish corpus of over 34,000 medical questions and answers. A search was then conducted to identify the optimal hyperparameter configuration using heuristic methods and nonlinear regression models. The evaluation of MédicoBERT was carried out using metrics such as perplexity to measure the adaptation of the language model to the medical vocabulary in Spanish, where it obtained a value of 4.28, and the average F1 metric for the task of answering medical questions, where it obtained a value of 62.35%. The objective of MédicoBERT is to provide support for research in the field of natural language processing (NLP) in Spanish, with a particular emphasis on applications within the medical domain.

Depression is a prevalent mental health disorder, and early detection is crucial for effective intervention. Recent advancements in eye-tracking technology and machine learning offer new opportunities for non-invasive diagnosis. This study aims to assess the performance of different machine learning algorithms in. predicting depression in a young sample using eye-tracking metrics. Eye-tracking data from 139 participants were recorded with an emotional induction paradigm in which each participant observed a set of positive and negative emotional stimuli. The data were analyzed to find differences between groups, where the most significant features were selected to train prediction models. The dataset was then split into training and testing sets using stratified sampling. Four algorithms support vector machines (SVM), random forest (RF), a multi-layer perceptron (MLP) neural network, and gradient boosting (GB) were trained with hyperparameter optimization and 5-fold cross-validation. The RF algorithm achieved the highest accuracy at 84%, followed by SVM, GB, and the MLP neural network. Performance metrics such as accuracy, recall, F1-score, precision recall area under the curve (PR-AUC), and Matthews Correlation Coefficient (MCC) were also used to evaluate the models. The findings suggest that eye-tracking metrics combined with machine learning algorithms can effectively identify depressive symptoms in the young, indicating their potential as non-invasive diagnostic tools in clinical settings.