Here is the research we’ve found on cyberbullying in Mexico, with the most recent first. Please email us if you have any articles to add with the details ordered in the same format as the others.



Authors: Arce-Ruelas, K.I., Alvarez-Xochihua, O., Pellegrin, L., Cardoza-Avendaño, L., and González-Fraga, J.A.

Year: 2022

Title: Automatic Cyberbullying Detection: a Mexican case in High School and Higher Education students

Journal: IEEE Latin America Transactions


Abstract: The social interaction among young students has been partially or totally transformed to mobile-based communication, specifically through the use of social networks. This new communication environment has allowed a more immediate, diverse and massive interaction, offering a faster and more effective situation when carrying out academic and recreational activities. However, this scenario has also promoted the phenomenon of social harassment known as bullying, exponentially increasing its scope and diversifying the types and forms of aggression. Machine learning and natural language processing techniques have been used to create models that detect bullying situations among students, using data corpus from mainly public social networks. However, generally, these data sources are not representative of the social networks commonly used by the students; generating classification models that do not consider the vocabulary used by this social group. This article describes the methodology used to create a representative data corpus of the interaction between Mexican high school and university students, and a comparative analysis on characteristics that influence the quality of the content of a corpus in this domain. In addition, the performance achieved by implementing various machine learning models to identify bullying situations is presented. The best result is reported for the Naive Bayesian classifier (F1-Score of 0.862), performing better than models based on deep learning such as Recurrent (F1-Score of 0.845) and Convolutional (F1-Score of 0.807) Neural Networks.



Authors: Esparza-Del Villar, O.A.,Chavez-Valdez, S.M., Montañez-Alvarado, P., Gutiérrez-Vega, M., and Gutiérrez-Rosado, T.

Year: 2021

Title: Relationship Between Different Types of Violence and Mental Health in High School Students From Northern Mexico

Journal: Journal of Interpersonal Violence


Abstract: Different types of violence have been present in Mexico but there have been few studies that have analyzed their relationship with mental health in adolescents, especially in cities with high rates of social violence. It is important to compare different violence types and their relationship with mental health since not all relationships are the same. It appears that social violence has a stronger relationship with mental health, and for this reason it receives more attention, but other types of violence have a stronger relationship and do not receive as much attention. Chihuahua has been one of the most violent states in Mexico, and Juarez has been the most violent city in the world in 2009 and 2010. The purpose of the study is to compare the relationship of different types of violence (social, cyberbullying, partner violence, and child abuse and neglect) with mental health indicators (depression, anxiety, stress, self-esteem, and paranoid thoughts). There were 526 high school students, from the cities of Juarez (n = 282) and Chihuahua (n = 244). The mean age was 16.5 (SD = 1.4) years and 50.6% reported being males. The relationships among the variables were analyzed using Pearson’s correlations and multiple linear regressions. Both cities that have experienced social violence like carjacking, kidnapping, and sexual assault, but they have very small or no relationships with mental health indicators. Other types of violence have stronger correlations. Our findings suggest that interventions should not focus only in preventing and dealing with social violence, but that other types of violence must also be addressed in adolescents.



Authors: Manuel Lepe-Faúndez, Alejandra Segura-Navarrete, Christian Vidal-Castro, Claudia Martínez-Araneda, and Clemente Rubio-Manzano

Year: 2021

Title: Detecting Aggressiveness in Tweets: A Hybrid Model for Detecting Cyberbullying in the Spanish Language



Abstract: 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.



Authors: Martín-Babarro, J., Toldos, M.P., Paredes-Becerra, L., Abregu-Crespo, R., Fernández-Sánchez, J., and Díaz-Caneja, C.M.

Year: 2021

Title: Association of Different Forms of Child Maltreatment With Peer Victimization in Mexican Children and Adolescents

Journal: Frontiers in Psychology


Abstract: To examine the relationship between exposure to multiple forms of child abuse and neglect within the family context and peer victimization at school, accounting for the moderator effect of sex and educational level. Two thousand four hundred fifteen children and adolescents, aged 9 to 15 years, attending public schools in Mexico completed the Childhood Trauma Questionnaire-Short Form and a modified version of the Olweus’ Bully/Victim Questionnaire. We used linear regression models to assess the association of five different forms of child abuse (emotional, physical, and sexual abuse, and emotional and physical negligence) with three forms of peer victimization (direct, indirect, and cyberbullying). Direct forms of child abuse within the family (i.e., emotional, physical, and sexual abuse), but not neglect, were significantly and positively associated with a risk for peer victimization. In the fully adjusted models, emotional abuse was significantly associated with the three types of peer victimization: [indirect b = 0.48, t = 6.75, p < 0.001, direct (b = 0.47, t = 4.89, p < 0.001), and cyberbullying (b = 0.85, t = 5.45, p < 0. 001)]; while physical abuse was positive and significantly associated with direct victimization (b = 0.29, t = 3.28, p < 0.001). Boys suffering from sexual abuse within the family context showed higher levels of all subtypes of peer victimization. Students attending secondary school who suffered from sexual abuse showed higher levels of indirect victimization than did students attending primary schools. Child abuse within the family context seems to be associated with the risk of peer victimization. Preventive strategies to address bullying and promote resilience should take family factors into account. Interventions for high-risk families might be useful to prevent child multi-victimization.



Authors: Aparain, Angeles, Sanin, Rosana and Cecchi, Velleda.

Year: 2020

Title: Psychoanalytic and systematic research on cyberbullying in high school students from Argentina, Mexico and Uruguay

Journal: International Conference of Research and Professional Practice in Psychology


Abstract: This paper will present the progress of a research accredited by the Argentine Psychoanalytic Association, which aims to explore the subjective and bonding characteristics of cyberbullying (victims and perpetrators) from a psychoanalytic perspective. The sample consisted of 329 participants (adolescents between 15 and 18 years of age from Argentina, Mexico and Uruguay) through the administration of a questionnaire with open questions used by Lanzilloti and Korman. In addition, an interview was conducted with an 18-year-old girl from Sinaloa, Mexico who went through a situation of cyberbullying and identity theft on social networks. The analysis of the information was carried out using the classical psychoanalytic method. Different axes of analysis were identified from the crossover between the questionnaires and the interview: 1) The difficulty of the victim to disconnect with the scene since there is a constant interaction with the cell phone or the computer. 2) Invisibility on the part of the harasser while hiding through anonymity, pseudonyms or false accounts. 3) Mastery drive or empowerment. 4) I fixed or in regression to the functioning of the purified I-pleasure. These concepts will be discussed in such a way that they allow addressing the intersubjective plot present in situations of cyberbullying.



Authors: Pozaz Rivera, J., Morales Reynoso, T., & Martinez-Vilchis, R.

Year: 2018

Title: Efectos de un programa de ciberconvivencia en la prevención del cyberbullying. (Spanish)

Journal: Psychology, Society & Education

URL: DOI: 10.25115/psye.v10i2.1953

Abstract: With the use of virtual environments as means of socialization, problems such as bullying have been transferred to cyberspace. Although cyberbullying is a current problem within educational institutions, there are few proposals for programs that seek to enable children to learn to use and coexist in an adequate way in virtual environments. The objective of this research is that students show an appropriate behavior in the interpersonal relationships they have in virtual environments through the implementation of a program based on cyber-survival, and with it, a decrease in cyberbullying. The evaluation of the effectiveness of this program was carried out by means of a quasi-experimental pretest-posttest design, with a control group without exposure to the program (N = 44) and an experimental group with exposure (N = 44) Of high school with ages between 15 and 18 years. Among the results obtained, we highlight the decrease in victimization and justification of cyberbullying in the experimental group and remaining in the control group.



Authors: Di Capua, M., Di Nardo, E., & Petrosino, A

Year: 2016

Title: Unsupervised cyberbullying detection in social networks.

Journal: 23rd International Conference on Pattern Recognition (ICPR), Pattern Recognition

URL: 10.1109/ICPR.2016.7899672

Abstract: Modern young people (“digital natives”) have grown in an era dominated by new technologies where communications are pushed to quite a real-time level, and pose no limits in establishing relationships with other people or communities. However, the speed of evolution does not allow young people to split consciously acceptable behaviors from potentially harmful ones and a new phenomenon known as cyber bullying is emerging with increasing evidence, attracting the attention of educators, and media. Cyber bullying is defined as “willful and repeated harm inflicted through the use of electronic devices” [1]. In this paper we propose a possible solution for automatic detection of bully traces over a social network, using techniques derived from NLP (Natural Language Processing) and machine learning. Specifically, we shall design a model inspired by Growing Hierarchical SOMs, able to cluster efficient documents containing bully traces, built upon semantic and syntactic features of textual sentences. We fine-tuned our model to work with the social network Twitter, but we also tested the model against other social networks such as YouTube and Formspring. Finally, we report our results, showing that the proposed unsupervised approach could be effectively used with good performances in some scenarios.



Authors: Del Río Pérez, Jorge; Bringué, Xavier; Sádaba, Charo; González González, Diana.

Year: 2009

Title: Cyberbullying: un análisis comparativo en estudiantes de Argentina, Brasil, Chile, Colombia, México, Perú y Venezuela. En: Generació digital: oportunitats i riscos dels públics

Journal: La transformació dels usos comunicatius. V Congrés Internacional Comunicació i Realitat.


Abstract: This study explores the issue of cyberbullying from a cross-cultural perspective. The focus is on the examination of the extent of Argentina, Brazil, Chile, Colombia, México, Peru, Venezuela tweens and adolescents’ experiences of cyberbullying. A survey study of 21.000 students from 10 to 18 years. In this paper, “cyberbullying” refers to bullying via electronic communication tools: mobile phone/video/picture/text message, Internet/gaming/instant messaging.



Author(s): Gámez-Guadix, M., Villa-George, F., & Calvete, E.

Year: 2014

Title: Psychometric properties of the Cyberbullying Questionnaire (CBQ) among Mexican adolescents.

Journal: Violence and victims


Abstract: The first objective of this study was to analyze the psychometric properties of the Cyberbullying Questionnaire (CBQ), an instrument for measuring the perpetration and victimization of bullying via new technologies for adolescents. The second objective was to analyze gender differences in the prevalence of cyberbullying. The study sample consisted of 1,491 Mexican adolescents (52.4% male and 47.6% female) with a mean age of 14.51 years (SD = 1.57, range = 12-18). A confirmatory factor analysis of the CBQ indicated a good fit of a model consisting of two factors designated as “perpetration” and “victimization.” The internal consistencies for these subscales were adequate. Furthermore, multiple-group-covariance-structure analysis with the Mexican and a Spanish sample (N = 1008; 55.7% girls; mean age = 15.23 years, SD = 1.4) indicated equivalence of the factor structure of the CBQ across samples. An analysis of the relationship between the CBQ and other variables-such as the justification of cyberbullying, impulsivity, and depression-provided additional data supporting the construct validity of the instrument. Regarding gender differences in the prevalence of CB, perpetration was significantly higher for males than for females, whereas no differences were found for victimization. Finally, we discuss the contributions of this work to the field of study.