Aymé Alejandra Escobar

Ms. Aymé Alejandra Escobar

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 November 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
AEAymé Alejandra Escobar
Aymé Alejandra Escobar
RRRicardo Rivadeneira
Ricardo Rivadeneira
Walter FuertesWalter Fuertes
Walter Fuertes
Hate speech is a form of communicative expression that promotes or incites unjustified violence. The increase in hate speech on social media has prompted the development of automated tools for its detection, especially those that integrate emotional tone analysis. This study presents a systematic review of the literature, employing a combination of PRISMA and PICOS methodologies to identify the most used Machine Learning techniques and Natural Language Processing emotion classification in hostile messages. It also seeks to determine which models and tools predominate in the analyzed studies. The findings highlight LLaMA 2 and HingRoBERTa, achieving F1 scores of 100% and 98.45%, respectively. Furthermore, key challenges are identified, including linguistic bias, language ambiguity, and the high computational demands of some models. This review contributes an updated overview of the state of the art, highlighting the need for more inclusive, efficient, and interpretable approaches to improve automated moderation on digital platforms. Additionally, it includes techniques, methods, and future directions in this topic.

31 October 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
AEAymé Alejandra Escobar
Aymé Alejandra Escobar
RRRicardo Rivadeneira
Ricardo Rivadeneira
Walter FuertesWalter Fuertes
Walter Fuertes
Hate speech is a form of communicative expression that promotes or incites unjustified violence. The increase in hate speech on social media has prompted the development of automated tools for its detection, especially those that integrate emotional tone analysis. This study presents a systematic review of the literature, employing a combination of PRISMA and PICOS methodologies to identify the most used Machine Learning techniques and Natural Language Processing emotion classification in hostile messages. It also seeks to determine which models and tools predominate in the analyzed studies. The findings highlight LLaMA 2 and HingRoBERTa, achieving F1 scores of 100% and 98.45%, respectively. Furthermore, key challenges are identified, including linguistic bias, language ambiguity, and the high computational demands of some models. This review contributes an updated overview of the state of the art, highlighting the need for more inclusive, efficient, and interpretable approaches to improve automated moderation on digital platforms. Additionally, include techniques, methods, and future directions in this topic.

4 November 2025
Verified
Report
Closed access
AEAymé Alejandra Escobar
Aymé Alejandra Escobar
RRRicardo Rivadeneira
Ricardo Rivadeneira
Walter FuertesWalter Fuertes
Walter Fuertes
INPLASY2025110006 Emotional Tone Detection in Hate Speech Using Machine Learning and NLP: Methods, Challenges, and Future Directions, a Systematic Review Keywords: Emotional tone; hate speech; mach…

20 April 2026 in Future Internet
Verified
Journal Article
Open access
PDF file
AEAymé Alejandra Escobar
Aymé Alejandra Escobar
RRRicardo Rivadeneira
Ricardo Rivadeneira
Walter FuertesWalter Fuertes
Walter Fuertes
WHWashington Eduardo Loza Herrera
Washington Eduardo Loza Herrera
Hate speech on social media reproduces norms of inequality and gender stereotypes, disproportionately affecting women. This study proposes a hybrid approach that integrates emotional tone classification with explicit hostility detection to strengthen preventive moderation. We constructed a corpus from three open data sets (1,236,371 records; 1,003,991 after ETL) and represented the text using TF-IDF and contextual RoBERTa embeddings. We trained individual models (RoBERTa fine-tuned, Random Forest, and XGBoost) and a stacking metamodel (Gradient Boosting) that combines their probabilities. On the test set, the ensemble outperformed the base classifiers, achieving accuracy of 0.93 in hate detection and 0.90 in emotion classification, with an AUC of 0.98 for emotion classification. We implemented a RESTful API and a web client to validate the moderation flow before publication, along with an administration panel for auditing. Performance tests in a prototype deployment (Google Colab exposed through an Ngrok tunnel) provided proof-of-concept validation, revealing concurrency limitations from around 300 users due to infrastructure constraints. In general, the results indicate that incorporating emotional tone analysis improves the model’s ability to identify implicit hostility and offers a practical way to promote safer digital environments. The probabilistic outputs produced by the ensemble model were subsequently analyzed using the Bayesian Calibration and Optimal Design under Asymmetric Risk (BACON-AR) framework, which serves as a mathematical post hoc decision layer for evaluating classification behaviour under unequal error costs. Rather than modifying the trained architecture or improving its predictive performance, the framework identifies a cost-sensitive operating threshold that minimizes the total expected risk under the selected asymmetric cost configuration. The experiments were conducted using an English-language data set; therefore, the findings of this study are limited to hate speech detection in English.

4 March 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
AEAymé Alejandra Escobar
Aymé Alejandra Escobar
RRRicardo Rivadeneira
Ricardo Rivadeneira
Walter FuertesWalter Fuertes
Walter Fuertes
WHWashington Eduardo Loza Herrera
Washington Eduardo Loza Herrera
Hate speech on social media reproduces norms of inequality and gender stereotypes, disproportionately affecting women. This study proposes a hybrid approach that integrates emotional tone classification with explicit hostility detection to strengthen preventive moderation. We constructed a corpus from three open datasets (1,236,371 records; 1,003,991 after ETL) and represented the text using TF-IDF and contextual RoBERTa embeddings. We trained individual models (RoBERTa fine-tuned, Random Forest, and XGBoost) and a stacking metamodel (Gradient Boosting) that combines their probabilities. On the test set, the ensemble outperformed the base classifiers, achieving accuracy of 0.93 in hate detection and 0.90 in emotion classification, with an AUC of 0.98 for emotion classification. We implemented a RESTful API and a web client to validate the moderation flow before publication, along with an administration panel for auditing. Performance tests showed viability under moderate loads and concurrency limitations starting at 300 users, associated with deployment via an Ngrok tunnel. In general, the results indicate that incorporating emotional tone analysis improves the model's ability to identify implicit hostility and offers a practical way to promote safer digital environments. The probabilistic results obtained by the ensemble model were subsequently analyzed using the Bayesian Calibration and Optimal Design under Asymmetric Risk (BACON-AR) framework, which serves as a mathematical post-hoc validation layer to optimize the decision threshold under unequal costs. This framework does not modify the trained architecture but adjusts the estimated probabilities and selects the threshold that minimizes the total expected risk. By combining TF-IDF and RoBERTa embeddings with a stacked metamodel, the ensemble's decision function was optimized via regularization, improving generalizability and the stability of predictions. The incorporation of the BACON-AR framework strengthened the system's probabilistic consistency, ensuring that final decisions were aligned with the actual consequences of errors under an asymmetric risk scheme.