Some previous studies have focused on using physiological signals to detect stress in individuals with ASD through wearable devices, yet few have focused on how to design such solutions. Wearable technology may be a valuable tool to aid parents and caregivers in monitoring the emotional states of individuals with ASD who are at high risk of experiencing very stressful situations. However, effective wearable devices for individuals with ASD may need to differ from solutions for those without ASD. People with ASD often have sensory sensitivity and may, therefore, not tolerate certain types of accessories and experience discomfort when using them. We used the Scopus, PubMed, WoS, and IEEE-Xplore databases to search for studies published from 2014 to 2024 to answer four research questions related to wearable solutions for individuals with ASD, physiological parameters, and techniques/processes used for stress detection. Our review found 31 articles; not all studies considered individuals with ASD, and some were beyond the scope of this review. Most of the studies reviewed are based on cardiac activity for stress monitoring using photoplethysmography (PPG) and electrocardiography (ECG). However, limitations include small sample sizes, variability in study conditions, and the need for customization in stress detection algorithms. In addition, there is a need to customize the stress threshold due to the device’s high individual variability and sensitivity. The potential of wearable solutions for stress monitoring in ASD is evident, but challenges include the need for user-friendly and unobtrusive designs and integrating these technologies into comprehensive care plans.

Assigning predefined classes to natural language texts, based on their content, is a necessary component in many tasks in organizations. This task is carried out by classifying documents within a set of predefined categories using models and computational methods. Text representation for classification purposes has traditionally been performed using a vector space model due to its good performance and simplicity. Moreover, the classification of texts via multilabeling has typically been approached by using simple label classification methods, which require the transformation of the problem studied to apply binary techniques, or by adapting binary algorithms. Over the previous decade, text classification has been extended using deep learning models. Compared to traditional machine learning methods, deep learning avoids rule design and feature selection by humans, and automatically provides semantically meaningful representations for text analysis. However, deep learning-based text classification is data-intensive and computationally complex. Interest in deep learning models does not rule out techniques and models based on shallow learning. This situation is true when the set of training cases is smaller, and when the set of features is small. White box approaches have advantages over black box approaches, where the feasibility of working with relatively small sets of data and the interpretability of the results stand out. This research evaluates a weighting function of the words in texts to modify the representation of the texts during multilabel classification, using a combination of two approaches: problem transformation and model adaptation. This weighting function was tested in 10 referential textual data sets, and compared with alternative techniques based on three performance measures: Hamming Loss, Accuracy, and macro-$F_1$. The best improvement occurs on the macro-$F_1$ when the data sets have fewer labels, fewer documents, and smaller vocabulary sizes. In addition, the performance improves in data sets with higher cardinality, density, and diversity of labels. This proves the usefulness of the function on smaller data sets. The results show improvements of more than 10% in terms of macro-$F_1$ in classifiers based on our method in almost all of the cases analyzed.