RT journal article
T1 Detecting Aggressiveness in Tweets: A Hybrid Model for Detecting Cyberbullying in the Spanish Language
A1 Lepe-Faúndez, Manuel
A1 Segura-Navarrete, Alejandra
A1 Vidal-Castro, Christian
A1 Martinez-Araneda, Claudia
A1 Rubio Manzano, Clemente
A2 Matemáticas
K1 cyberbullying detect
K1 emotions analysis in Spanish
K1 hybrid approach
AB In recent years, the use of social networks has increased exponentially, which has led to asignificant increase in cyberbullying. Currently, in the field of Computer Science, research has beenmade on how to detect aggressiveness in texts, which is a prelude to detecting cyberbullying. In thisfield, 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 badwords in a sentence using a Lexicon of bad words, which serves as an input feature for classificationalgorithms. This research aims at contributing towards detecting aggressiveness in Spanish languagetexts by creating different models that combine the Lexicons and ML approach. Twenty-two modelsthat 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 resultsin 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 the3 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 applicabilityto each model by classifying tweets, allowing evaluating the performance of models with externalcorpus and receiving feedback on the prediction of each one for future research. In addition, an APIis available that can be integrated into technological tools for parental control, online plugins forwriting analysis in social networks, and educational tools, among others.
PB MDPI
SN 2076-3417
YR 2021
FD 2021-11
LK http://hdl.handle.net/10498/26728
UL http://hdl.handle.net/10498/26728
LA eng
DS Repositorio Institucional de la Universidad de Cádiz
RD 13-nov-2026