In recent years, the use of social networks has increased exponentially, which has led to a significant increase in cyberbullying. Currently, in the field of Computer Science, research has been made on how to detect aggressiveness in texts, which is a prelude to detecting cyberbullying. In this field, the main work has been done for English language texts, mainly using Machine Learning (ML) approaches, Lexicon approaches to a lesser extent, and very few works using hybrid approaches. In these, Lexicons and Machine Learning algorithms are used, such as counting the number of bad words in a sentence using a Lexicon of bad words, which serves as an input feature for classification algorithms. This research aims at contributing towards detecting aggressiveness in Spanish language texts by creating different models that combine the Lexicons and ML approach. Twenty-two models that combine techniques and algorithms from both approaches are proposed, and for their application, certain hyperparameters are adjusted in the training datasets of the corpora, to obtain the best results in the test datasets. Three Spanish language corpora are used in the evaluation: Chilean, Mexican, and Chilean-Mexican corpora. The results indicate that hybrid models obtain the best results in the 3 corpora, over implemented models that do not use Lexicons. This shows that by mixing approaches, aggressiveness detection improves. Finally, a web application is developed that gives applicability to each model by classifying tweets, allowing evaluating the performance of models with external corpus and receiving feedback on the prediction of each one for future research. In addition, an API is available that can be integrated into technological tools for parental control, online plugins for writing analysis in social networks, and educational tools, among others.

Hopfield Neural Networks (HNNs) are recurrent neural networks used to implement associative memory. They can be applied to pattern recognition, optimization, or image segmentation. However, sometimes it is not easy to provide the users with good explanations about the results obtained with them due to mainly the large number of changes in the state of neurons (and their weights) produced during a problem of machine learning. There are currently limited techniques to visualize, verbalize, or abstract HNNs. This paper outlines how we can construct automatic video-generation systems to explain its execution. This work constitutes a novel approach to obtain explainable artificial intelligence systems in general and HNNs in particular building on the theory of data-to-text systems and software visualization approaches. We present a complete methodology to build these kinds of systems. Software architecture is also designed, implemented, and tested. Technical details about the implementation are also detailed and explained. We apply our approach to creating a complete explainer video about the execution of HNNs on a small recognition problem. Finally, several aspects of the videos generated are evaluated (quality, content, motivation and design/presentation).

Over the last ten years, social media has become a crucial data source for businesses and researchers, providing a space where people can express their opinions and emotions. To analyze this data and classify emotions and their polarity in texts, natural language processing (NLP) techniques such as emotion analysis (EA) and sentiment analysis (SA) are employed. However, the effectiveness of these tasks using machine learning (ML) and deep learning (DL) methods depends on large labeled datasets, which are scarce in languages like Spanish. To address this challenge, researchers use data augmentation (DA) techniques to artificially expand small datasets. This study aims to investigate whether DA techniques can improve classification results using ML and DL algorithms for sentiment and emotion analysis of Spanish texts. Various text manipulation techniques were applied, including transformations, paraphrasing (back-translation), and text generation using generative adversarial networks, to small datasets such as song lyrics, social media comments, headlines from national newspapers in Chile, and survey responses from higher education students. The findings show that the Convolutional Neural Network (CNN) classifier achieved the most significant improvement, with an 18% increase using the Generative Adversarial Networks for Sentiment Text (SentiGan) on the Aggressiveness (Seriousness) dataset. Additionally, the same classifier model showed an 11% improvement using the Easy Data Augmentation (EDA) on the Gender-Based Violence dataset. The performance of the Bidirectional Encoder Representations from Transformers (BETO) also improved by 10% on the back-translation augmented version of the October 18 dataset, and by 4% on the EDA augmented version of the Teaching survey dataset. These results suggest that data augmentation techniques enhance performance by transforming text and adapting it to the specific characteristics of the dataset. Through experimentation with various augmentation techniques, this research provides valuable insights into the analysis of subjectivity in Spanish texts and offers guidance for selecting algorithms and techniques based on dataset features.

Purpose: This article examines how generative artificial intelligence (GenAI) can improve students’ programming skills through timely feedback. Specifically, it evaluates the effectiveness of feedback provided through two custom-developed applications: (1) A chatbot-like virtual assistant powered by the GPT-4o-mini model designed to assist students interactively; (2) A programming platform that combines GenAI-generated feedback and a virtual judge for source code evaluation. The study explores whether these tools contribute to improving students’ programming performance. Method: The proposed method consists of the following tasks: (1) Development of two functional prototypes powered by GPT-4o-mini, the first of them a conversational chatbot with access to a specific programming knowledge base, and the second an innovative development that integrates in a single platform a GenAI and an open-source virtual judge for the joint generation of an automated assessment and timely feedback of the source code. (2) Designing and executing the experiment to evaluate whether providing feedback to students in a beginner programming course using GEN’s AI-based tools improved the passing rate in an assessment. To achieve this, a quasi-experimental study was conducted in which students engaged in context-enriched problem-solving. Two-course sections served as experimental groups, receiving feedback from the AI tools. At the same time, the other two groups served as controls. (3) Measuring students’ performance in problem-solving and collecting student perceptions on usability for the chatbot and the competitive programming platform. Results and Conclusions: Students who received feedback generated by GenAI did not show improvement in their performance, although they perceived it as useful. Conversational (tutorB@t) and non-conversational platform (tutorBot+) versions are available at https://cdn.botpress.cloud/webchat/v3.2/shareable.html?configUrl=https://files.bpcontent.cloud/2025/01/20/23/20250120232250-Q9SCHBOO.json and https://supc.ucsc.cl:23380/, respectively, under an AGPL 1.0 license. From the processing and analysis, a good perception of the usability of both tools was obtained (70.6% and 65.2%, respectively), which is reinforced by the 81% and 79% of students who stated that they would use them again. Although the usefulness and perception of the tools are considered positive, there is insufficient evidence to definitively evaluate the effect of GenAI-generated feedback on students’ passing rates in an assessment.

This study aims to detect instances of gender-based violence (GBV) in song lyrics in Spanish using a deep neural network (DL) model. The hypothesis is that the performance of the detection model can be enhanced through the application of data augmentation and undersampling techniques in the corpus generation process. The methodology involved retrieving song lyrics via web scraping and their labeling by three annotators based on gender-based violence categories defined by the Chilean Prosecutor's Office using a custom-built application. The experiments were conducted by training BETO, a BERT model pre-trained with Spanish texts. The results validated the hypothesis that the best performance in identifying gender-based violence in texts was found when the model was trained and tested with the augmented and undersampled dataset. As a result, a labeled corpus was created for training the model consisting of 1,200 labeled data containing expressions of gender-based violence collected from song lyrics. This resource was called GVL Corpus Spanish and is available in a public repository under a Creative Commons Attribution 4.0 International license, accessible to the scientific community. It is crucial to emphasize the importance of combining technology with education, awareness, and inclusive policies to foster respect and equality in human communication.