Search results

With the rise of social media platforms, an increasing number of cases of cyberbullying has reemerged. Every day, large number of people, especially teenagers, become the victim of cyber abuse. A cyberbullied person can have a long-lasting impact on his mind. Due to it, the victim may develop social anxiety, engage in self-harm, go into depression or in the extreme cases, it may lead to suicide. This paper aims to evaluate various techniques to automatically detect cyberbullying from tweets by using machine learning and deep learning approaches.

The authors applied machine learning algorithms approach and after analyzing the experimental results, the authors postulated that deep learning algorithms perform better for the task. Word-embedding techniques were used for word representation for our model training. Pre-trained embedding GloVe was used to generate word embedding. Different versions of GloVe were used and their performance was compared. Bi-directional long short-term memory (BLSTM) was used for classification.

The dataset contains 35,787 labeled tweets. The GloVe840 word embedding technique along with BLSTM provided the best results on the dataset with an accuracy, precision and F1 measure of 92.60%, 96.60% and 94.20%, respectively.

If a word is not present in pre-trained embedding (GloVe), it may be given a random vector representation that may not correspond to the actual meaning of the word. It means that if a word is out of vocabulary (OOV) then it may not be represented suitably which can affect the detection of cyberbullying tweets. The problem may be rectified through the use of character level embedding of words.

The findings of the work may inspire entrepreneurs to leverage the proposed approach to build deployable systems to detect cyberbullying in different contexts such as workplace, school, etc and may also draw the attention of lawmakers and policymakers to create systemic tools to tackle the ills of cyberbullying.

Cyberbullying, if effectively detected may save the victims from various psychological problems which, in turn, may lead society to a healthier and more productive life.

The proposed method produced results that outperform the state-of-the-art approaches in detecting cyberbullying from tweets. It uses a large dataset, created by intelligently merging two publicly available datasets. Further, a comprehensive evaluation of the proposed methodology has been presented.

This study aims to investigate students’ perceptions regarding the causes and effects of cyberbullying among university students. The study also establishes whether or not there would be statistically significant differences among cyberbullying victims, perpetrators, victim-perpetrators and bystanders in their thoughts on the causes and effects of cyberbullying on students’ social lives from a developing country perspective.

This study uses quantitative approach and cross-sectional survey design to collect primary data from 1,374 undergraduate students sampled from selected public universities in Ghana. Descriptive statistics and analysis of variance analyses were carried out using statistical package for the social sciences.

The study reports popularity among friends, extortion, retaliation, stress, trauma and low self-esteem as causes of cyberbullying. Also, cyberbullying resulted in difficulty trusting people, low self-esteem and increased stress. The study also found statistically significant differences among cyberbullying victims, perpetrators, victim-perpetrators and bystanders in their thoughts on the causes and effects of cyberbullying on students’ social lives.

The study’s findings imply that cyberbullying has some fairly significant negative effects on students’ lives in Ghana and must be taken more seriously. Conditions must be created to ensure that perpetrators and victims are given the support needed to curb this menace. Detailed remediating measures are provided in the study.

This paper contributes to the existing literature by studying cyberbullying perceptions among students from a relatively bully-tolerant culture.

This study aims to examine the effects of cyberbullying on the academic lives of Ghanaian university students. It also establishes whether cyberbullying victims, perpetrators, victim-perpetrators and bystanders differed in their thoughts on the effects of cyberbullying on students’ academic lives.

This study is anchored on Bandura’s theory of triadic reciprocal determinism and Abraham Maslow’s theory of needs. This study uses a cross-sectional survey design and quantitative approach to collect the data from 1,374 students from three public universities. The authors use descriptive statistics and ANOVA techniques to analyse the data.

The results show that the effects of cyberbullying on academic life are difficulty concentrating on studies, difficulty studying in groups and difficulty assessing important academic information online. There is also a statistically significant difference among cyberbullying victims, perpetrators, victim-perpetrators and bystanders in their thoughts on the effects of cyberbullying on students’ academic lives.

This research contributes to the literature on cyberbullying in the Ghanaian tertiary education environment. Even though the impact of cyberbullying on academics in Ghanaian universities may seem minimal, it is still imperative that it be checked, as it is significant enough to disrupt effective academic work. Thus, this study adds to the existing literature on cyberbullying from a developing country perspective.

The purpose of this study/paper To focus on finding COVID-19 with the help of DarkCovidNet architecture on patient images.

We used machine learning techniques with convolutional neural network.

Detecting COVID-19 symptoms from patient CT scan images.

This paper contains a new architecture for detecting COVID-19 symptoms from patient computed tomography scan images.

This purpose of this study is to perfrom the analysis of COVID-19 with the help of blood samples. The blood samples used in the study consist of more than 100 features. So to process high dimensional data, feature reduction has been performed by using the genetic algorithm.

In this study, the authors will implement the genetic algorithm for the prediction of COVID-19 from the blood test sample. The sample contains records of around 5,644 patients with 111 attributes. The genetic algorithm such as relief with ant colony optimization algorithm will be used for dimensionality reduction approach.

The implementation of this study is done through python programming language and the performance evaluation of the model is done through various parameters such as accuracy, sensitivity, specificity and area under curve (AUC).

The implemented model has achieved an accuracy of 98.7%, sensitivity of 96.76%, specificity of 98.80% and AUC of 92%. The results have shown that the implemented algorithm has performed better than other states of the art algorithms.

Nowadays people are connected by social media like Facebook, Instagram, Twitter, YouTube and much more. Bullies take advantage of these social networks to share their comments. Cyberbullying is one typical kind of harassment by making aggressive comments, abuses to hurt the netizens. Social media is one of the areas where bullying happens extensively. Hence, it is necessary to develop an efficient and autonomous cyberbullying detection technique.

In this paper, the authors proposed a transformer network-based word embeddings approach for cyberbullying detection. RoBERTa is used to generate word embeddings and Light Gradient Boosting Machine is used as a classifier.

The proposed approach outperforms machine learning algorithms such as logistic regression, support vector machine and deep learning models such as word-level convolutional neural networks (word CNN) and character convolutional neural networks with short cuts (char CNNS) in terms of precision, recall, F1-score.

One of the limitations of traditional word embeddings methods is context-independent. In this work, only text data are utilized to identify cyberbullying. This work can be extended to predict cyberbullying activities in multimedia environment like image, audio and video.

This study aims to examine social determinants and social strains of cyberbullying victimization among expatriate populations in high-income countries such as Qatar. The authors argue that expatriate students will be exposed to stains and pressures due to several factors, such as feeling alienated, lonely, homesick, insecure and helpless. This study examines a partial assumption of general strain theory (GST), which posits that expats’ cyberbullying victimization can create negative stimuli that lead to negative feelings and, as a result, to delinquent behavior. The delinquent behavior can be seen as a coping method in encountering strains. Logistic regression analysis is applied (using SPSS v. 21) to test the hypothesis that the victimization of expats’ cyberbullying could lead to strain and delinquency.

A sample of 2,428 expatriate students (46% males and 54% females) was randomly selected from seven public schools in Qatar. The average number of siblings in the household was 2.7. Around 10.8% of the sample reported victimization by cyberbullying. Most came from intact families (80.6%) compared to 19.4 living in broken homes. Concerning the birth order of the student in the family, 25% of the sample were firstborn, and 20% were middle-born. Students’ mother relationships were higher than students’ father relationships (69% vs 51%, respectively). Fathers were higher in undergraduate education than mothers (60% vs 49%, respectively). Considering that 58% of women did not have a job, most fathers work in administrative positions (47% in administrative work and 39% in professional positions) as opposed to mothers’ positions (15% and 21%, respectively). The survey was distributed among expatriate students by trained researchers, teachers and social workers in public schools. The researchers explained the purpose of the study, confidentiality and potential risks and provided directions for completing the survey. Parents and their children provided signed informed consent before participation, following the institutional review boards of Qatar University’s Human Subject Research Committee and the Ministry of Social Development. The victimization of cyberbullying is measured at the dichotomy level by asking a general cyberbullying question (In the last 12 months, had you been bullied by other students using mobile messages, email, voice or video messages? Responses were 1 – yes and 0 – no). A definition of cyberbullying was included in the questionnaire. Independent measures are as follows: (1) demographic variables: gender, belief, health, number of friends and exposure to violence; (2) family variables: delinquent family, coercive parenting, family relations, family disputes, father absence and family ties; (3) school variables: school satisfaction, school violence, student fighting, teachers' violence, school truancy and going late to school; (4) imprudent behavior: smoking, alcohol, not using a seat belt, gambling, stealing less than 100 QR, chewing tobacco, stimuli, volatile drugs, sexual harassment, throwing garbage out of the car, cheating, vandalism and victimization.

Findings showed that n = 255, 10.8% of the expats’ sample N = 2,428 reported victimization of cyberbullying, of whom 46% were males and 54% were females. A total of 24% of the victims of cyberbullying were males, and 5.8% were females. About a third of the sample were cyberbullying perpetrators (n = 716, 29.5%). Victims of cyberbullying came from intact families (62.4%) compared to broken families (37.6%). A round third of the victims reported the absence of a father during their childhood (n = 78, 31.7%). Most of the victims came from a typical community compared to the delinquent community (71.2% vs 28.2%). About a third of the victims reported it was easy to talk with the father when needed (32% compared to 42.7%), who said it was easy. More than half of the victims do not use seat belts. A low percentage of them were gambling (n = 68, 27% or 2.9% of the total sample). Regarding escaping imprudent and delinquent behaviors, findings showed that a third and more than a tenth of the cyberbullying were smokers and alcoholics (n = 69, 27.4% and n = 42, 16.7% respectively). Moreover, among the most serious, widely spread student problems, around a quarter of the victims reported using chewing tobacco (Sweeka is the local name) (n = 54, 21.4%). Finally, drug use among victims was more than a tenth of them (n = 41, 16.3%). About a quarter of the victims reported stealing less than 100 QR (n = 67, 26.8% or 2.9% of the total sample). Concerning the crimes committed by victims, findings showed that more than forth of them committed assault (n = 71, 28.3%), student fights (n = 202, 80.8%), school violence (n = 117, 46.6%) and half of the victims (50.2%) were also victims of face-to-face bullying. Little below half of the sample was exposed to violence (n = 120, 48.6%) and was the victim of violence in the past 12 months (n = 100, 40.8%). A significant gender differences was found in the victimization of cyberbullying (1 = yes, 0 = no) (a = 000). Moreover, significant mean differences were found between expatriates student victimization of cyberbullying at (a = 000) in all strain variables. Using binary regression analysis to examine the equality of probability of being a victim of cyberbullying as accounted for by the independent variables, the model’s predictability was 89.4%. The Hosmer and Lemeshow test and omnibus tests support the model’s fit (a = 000). Nagelkerke R² shows that the stain variables accounted for 24% of the variance in the expat's student victimization of cyberbullying.

Conceptualization and determination of what constitutes cyberbullying from the criminal law perspective are needed. Cyberbullying is defined as a form of violence and crime involving new technologies (Sun et al., 2016, p. 62). Policymakers should provide accessible and equitable access to the criminal justice system, the integration of expatriates and the provision of support services to avoid delinquency.

A social cohesion, inclusion and well-being policy is needed for expatriate students and their families in Qatar. In particular, cultural diversity policy and programs, a source of strength and enrichment should be promoted in educational settings. Social inclusion and cultural diversity programs could ease the alienation and marginalization that expatriate students may encounter in their host societies to prevent stains and negative emotions that lead to delinquency and criminal behaviors. Access to support services without discrimination to avoid health and psychological strains and risk factors. This includes but is not limited to avoidance of stigmatization, embarrassment, sense of helplessness, humiliation and other negative feelings toward expatriates. Awareness and promotion of cultural diversity values are needed to enhance cultural acceptance to reduce victimization among the expatriate population. Criminal law and security implications conceptualization and determination of what constitutes cyberbullying from the criminal law perspective are needed. Cyberbullying is a form of violence and crime involving new technologies (Sun et al., 2016). Policymakers should provide accessible and equitable access to the criminal justice system, integrating expatriates and providing support services to avoid delinquency. There is a pressing need for further research within the realm of crime and law to establish the precise legal boundaries surrounding cyberbullying and to delineate the potential scope for legislative measures aimed at safeguarding against victimization in Qatar. Although the state of Qatar has taken steps to address cyberbullying by incorporating it into relevant legal frameworks, there remains a gap in terms of specifically targeting cyberbullying involving children and adolescents. Despite the introduction of the new Cybercrime Prevention Law, the issue of cyberbullying among these vulnerable groups is not adequately addressed.

Social implication includes but is not limited to avoidance of stigmatization, embarrassment, sense of helplessness, humiliation and other negative feelings towards expatriate. Awareness and promotion of cultural diversity values is needed to enhance cultural acceptance to reduce victimization among expatriate population.

The present study examines some strain theory assumptions and the victimization of the cyberbullying expatriate population. This study tests a partial assumption of GST, which states that the expatriate population’s exposure to the victimization of cyberbullying can lead to negative stimuli that, in return, create negative feelings and, as a result, imprudent and delinquent behavior. The cyberbullying behavior can be seen as an escaping and coping method in encountering strains. This study underscores the presence of cyberbullying within high schools among expatriate students, exerting significant effects on their personal, social and emotional behaviors. The novel insights gleaned from this investigation contribute substantively to the comprehension of both the pervasiveness and repercussions of cyberbullying on the well-being of expatriate students. This contribution is particularly vital, given the dearth of research in the field, largely attributable to the growing dependence of students on the internet for various cyber activities. This study examines a partial assumption of GST (in non-Western country). Moreover, it uses an advanced statistical analysis and large sample.

This paper aims to explore the prevalence rate of adolescents engaging in aggressive behaviours towards their peers using the Internet and mobile phones, while examining the duration and intensity of this cyberbullying, and to analyse differences in cyberbullying behaviours based on gender and age (academic grades). Research on cyberbullying indicates that it is a global problem that is increasing dramatically among adolescents.

The sample was composed of 1,415 Spanish adolescents of both sexes (760 boys and 655 girls) between 12 and 17 years old (M = 13.9 years old; SD = 1.4).

The results indicated that the cyberbullying prevalence among adolescents in the past year was 32 per cent. Likewise, the data suggest that boys and students in their fourth year of secondary education (15-17 years old) perpetrated cyberbullying on their peers more than girls and students in lower grades.

The results presented in this research should be interpreted with caution due to its cross-sectional nature; a longitudinal study with measurements at different times would help to confirm the results observed here. On the other hand, in this study, the adolescents’ responses were obtained through self-reports and, although they could be subject to social desirability effects and biases, as indicated by Flisher et al. (2004), the reliability and validity of adolescent self-reports in the measurement of risk behaviours were quite acceptable.

It is of crucial importance to develop educational strategies designed to favour the responsible use of the new technologies. In many cases, children and adolescents are not aware of psychological and legal consequences that their cyber-aggressions can have on themselves, on the victims and on their families and social environment.

The authors feel that this research may contribute to clarifying some crucial issues related to the growing problem of cyberbullying that affects adolescents in many countries of the world. As the present research deals with aspects of interactive technology and smart education, the authors believe that the findings reported in the manuscript would be of interest to potential readers of this Journal.

This paper is an original perspective on cyberbullying aggressors among secondary education students in a Spanish context.

Cyberbullying has become one of the reasons behind the increase in psychological and medical problems. A need to prevent recurrences of cyberbullying incidents and discourage bullies from further bullying the victims has risen. This problem has attracted the attention of all stakeholders across the globe. Various researchers have developed theories and interventions to detect and stop bullying behavior. Previously, researchers focused on helping victims, but as the times have changed, so has the focus of researchers. This study aims to analyze scientific research articles and review papers to understand the development of the knowledge base on the topic.

This study analyzes the performance of literature on cyberbullying perpetration (CBP) using the widely accepted bibliometric analysis techniques: performance analysis and science mapping. The study is based on a dataset extracted from the Web of Science database. Initially, 2,792 articles between 2007 and 2022 were retrieved, which were filtered down to 441. The filter was based on various criteria, but primarily on CBP. VOSViewer and MS Excel were used to analyze the data. In addition, VOSViewer was used to create “bibliometric citations, co-citations, and co-word maps.”

The findings include publication and citation quantum and trends, the top 20 active countries, the most significant research articles and leading journals in this domain. Major themes or clusters identified were “Cyberbullying and victim behavior,” bullying behavior, adolescents and intervention, “cyberbullying associations,” and “cyberbullying personality associations.”

The study is unique because it analyses research articles based on cyberbullies, whereas past studies explored only the victims' side. Further, the present study used the Web of Science database, whereas most studies use the Scopus database.

This paper aims to study the developed countries’ experience on the cyberbullying legal regulation among adolescents, to identify existing shortcomings in the developing countries’ laws and to develop recommendations for regulatory framework improvement.

The authors have studied the state regulatory practice of the UK, the USA, Canada, Malaysia, South Africa, Turkey, UAE and analyzed the statistics of 2018 on the cyberbullying manifestation among adolescents in these countries.

The study results can encourage countries to create separate cyberbullying legislation and periodically review and modify already existing legislation.

The study provides a list of the recommendations to regulate cybercrime in developing countries and prevent it as well. The results may contribute to creating laws related to the regulation of cyberbullying in countries where such legislation does not exist yet or existing regulatory legal acts do not bring the expected results, namely, in Post-Soviet countries and other developing countries of the world.