The rise of social media has created a new platform for communication and interaction, but it has also facilitated the spread of harmful behaviors such as cyberbullying. Detecting and mitigating cyberbullying on social media platforms is a critical challenge that requires advanced technological solutions. This paper presents a novel approach to cyberbullying detection using a combination of supervised machine learning (ML) and natural language processing (NLP) techniques, enhanced by optimization algorithms. The proposed system is designed to identify (...) and classify cyberbullying behavior in real-time, analyzing textual data from social media posts to detect harmful content. The model is trained on a large dataset of labeled instances of bullying and non-bullying content, using supervised ML algorithms such as Support Vector Machines (SVM), Decision Trees, and Random Forest. NLP techniques, including sentiment analysis, keyword extraction, and text vectorization, are employed to preprocess and transform the data into a format suitable for machine learning. To optimize the performance of the detection model, techniques such as Grid Search, Genetic Algorithms, and Particle Swarm Optimization are used to fine-tune hyperparameters, resulting in improved accuracy and reduced false positives. The system's effectiveness is validated through experiments conducted on various social media platforms, demonstrating its potential to detect cyberbullying with high precision. Future work will focus on enhancing the model's adaptability to emerging slang and evolving language patterns in social media. Key words: Cyberbullying Detection, Social Media, Supervised Machine Learning, Natural Language Processing (NLP), Optimization Techniques. (shrink)

The rise of social media has created a new platform for communication and interaction, but it has also facilitated the spread of harmful behaviors such as cyberbullying. Detecting and mitigating cyberbullying on social media platforms is a critical challenge that requires advanced technological solutions. This paper presents a novel approach to cyberbullying detection using a combination of supervised machine learning (ML) and natural language processing (NLP) techniques, enhanced by optimization algorithms. The proposed system is designed to identify (...) and classify cyberbullying behavior in real-time, analyzing textual data from social media posts to detect harmful content. The model is trained on a large dataset of labeled instances of bullying and non-bullying content, using supervised ML algorithms such as Support Vector Machines (SVM), Decision Trees, and Random Forest. NLP techniques, including sentiment analysis, keyword extraction, and text vectorization, are employed to preprocess and transform the data into a format suitable for machine learning. T. (shrink)

The rise of social media has created a new platform for communication and interaction, but it has also facilitated the spread of harmful behaviors such as cyberbullying. Detecting and mitigating cyberbullying on social media platforms is a critical challenge that requires advanced technological solutions. This paper presents a novel approach to cyberbullying detection using a combination of supervised machine learning (ML) and natural language processing (NLP) techniques, enhanced by optimization algorithms. The proposed system is designed to identify (...) and classify cyberbullying behavior in real-time, analyzing textual data from social media posts to detect harmful content. The model is trained on a large dataset of labeled instances of bullying and non-bullying content, using supervised ML algorithms such as Support Vector Machines (SVM), Decision Trees, and Random Forest. NLP techniques, including sentiment analysis, keyword extraction, and text vectorization, are employed to preprocess and transform the data into a format suitable for machine learning. To optimize the performance of the detection model, techniques such as Grid Search, Genetic Algorithms, and Particle Swarm Optimization are used to fine-tune hyperparameters, resulting in improved accuracy and reduced false positives. The system's effectiveness is validated through experiments conducted on various social media platforms, demonstrating its potential to detect cyberbullying with high precision. Future work will focus on enhancing the model's adaptability to emerging slang and evolving language patterns in social media. (shrink)

Kustenmacher and Seiwert (2004) explain a man’s inclination to resort to technology in his interaction with the environment and society. Thus, the solution to the negative consequences of Cyberbullying in a technologically dominated society is represented by technology as part of the technological paradox (Tugui, 2009), in which man has a dual role, both slave and master, in the interaction with it. In this respect, it is noted that, notably after 2010, there have been many attempts to involve artificial (...) intelligence (AI) to recognize, identify, limit or avoid the manifestation of aggressive behaviours of the CBB type. For an overview of the use of artificial intelligence in solving various problems related to CBB, we extracted works from the Scopus database that respond to the criterion of the existence of the words “cyberbullying” and “artificial intelligence” in the Title, Keywords and Abstract. These articles were the subject of the content analysis of the title and, subsequently, only those that are identified as a solution in the process of recognizing, identifying, limiting or avoiding the manifestation of CBB were kept in the following Table where we have these data synthesized and organized by years. (shrink)

Cyber bullying affects many adolescents and teens on a daily basis; it is a form of violence that can do lasting harm to people at different ages and social status in a society. Cyber bullying is real experience that has been in existence for a quite a long time; Bullying statistics show that cyber bullying is a serious problem among teens and gaining roots among adults. By being more aware of cyber bullying, teens and adults can help to fight it. (...) Cyber bullying involves using technology, like cell phones and the Internet, to bully or harass another person. The introduction of social media and other communication systems has seen several people being bullied online by those who are already proficient on the platforms. The reasons behind cyber bullying might or might not be mala-fide but its existence isn’t in the best interest. It has been looked at mainly from the teens’ effect both in physical and psychological perception not realizing that adults are also equally affected. The impact on adults comes in different forms and has serious impact on the families and work places. The impact at work places affects productivity due to psychological trauma, legal involvement, shame/embarrassment whenever it goes public. Some people have gone to point of resigning from jobs, others have buried themselves into work for fear of victimization, others have committed suicide - At whatever level of status in society there is a great repercussion that is if situation is not put under control the victim can easily go down to a total down trend. Cyber bullying has fatal consequences and existing laws about it are woefully lacking despite some legal measures having been put in place but it gets tricky especially if the cyber bully is anonymous. There are cybercrime cells that help in preventing cyber bullying or minimize the happenings to set up a good working environment that may increase individual productivity and increase organisations profits. (shrink)

This research report presents findings about the extent and nature of digital self-harm among New Zealand teens. Digital self-harm is broadly defined here as the anonymous online posting or sharing of mean or negative online content about oneself. The report centres on the prevalence of digital self-harm (or self-cyberbullying) among New Zealand teens (aged 13-17), the motivations, and outcomes related to engaging in this behaviour. The findings described in this report are representative of the teenage population of New Zealand (...) by gender, ethnicity and age. Key findings are: Overall, 6% of New Zealand teens have anonymously posted mean or negative content online about themselves in the past year. Teenagers’ top reasons for this behaviour were: making a joke, wanting to show resilience, looking for friends’ sympathy, and seeking reassurance of friendship. By exploring the nature and extent of this behaviour, we are providing the online safety community, schools and parents with insights about a complex and, to some extent, hidden phenomenon involving New Zealand teens. (shrink)

While children’s experiences of online risks and harm is a growing area of research in New Zealand, public discussion on the matter has largely been informed by mainstream media’s fixation on the dangers of technology. At best, debate on risks online has relied on overseas evidence. However, insights reflecting the New Zealand context and based on representative data are still needed to guide policy discussion, create awareness, and inform the implementation of prevention and support programmes for children. This research report (...) presents findings from a quantitative study regarding different aspects related to risks and online safety. It looks at the online experiences that children find bothersome and upsetting and explores the hurtful behaviours they encounter or engage in, both online and in person. Evidence regarding exposure to different types of potentially harmful online content is also presented. Another relevant contribution is the insights related to excessive internet use.The findings presented in this report are based on data from 2,061 New Zealand children aged 9-17. We hope the findings will contribute to the development of policies, practices and services designed to support New Zealand children to safely take advantage of the opportunities available to them online. (shrink)

Unless and until our society recognizes cyber bullying for what it is, the suffering of thousands of silent victims will continue.” ~ Anna Maria Chavez. There had been series of research on cyber bullying which are unable to provide reliable solution to cyber bullying. In this research work, we were able to provide a permanent solution to this by developing a model capable of detecting and intercepting bullying incoming and outgoing messages with 92% accuracy. We also developed a chatbot automation (...) messaging system to test our model leading to the development of Artificial Intelligence powered anti-cyber bullying system using machine learning algorithm of Multinomial Naïve Bayes (MNB) and optimized linear Support Vector Machine(SVM). Our model is able to detect and intercept bullying outgoing and incoming bullying messages and take immediate action. (shrink)

While children’s interaction with digital technologies is a matter of interest around the world, evidence based on nationally representative data about how integrated these tools are in children’s everyday life is still limited in New Zealand. This research report presents findings from a study that explores children’s internet access, online skills, practices, and opportunities. This report is part of Netsafe’s research project Ngā taiohi matihiko o Aotearoa - New Zealand Kids Online, and our first publication as a member of Global (...) Kids Online. Generating insightful, reliable evidence about New Zealand children’s online experiences is vital to develop adequate support that reflects children’s experiences and needs. This, in turn, will help them to manage online risks and potential harm from behaviours such as cyberbullying, harassment, and other forms of abuse and intimidation. (shrink)

Introduction: During the COVID-19 pandemic, adolescents have increasingly suffered from online problem behaviors and mental disorders. But little research has paid attention to the protective factors among adolescents. Therefore, the present study attempted to investigate the role of positive youth development (PYD) attributes in adolescents’ depression, internet gaming disorder (IGD) and cyberbullying/victimization (CBV). -/- Methods: A total of 995 Chinese adolescents (Mage = 15.97 years, SD = 0.77, 325 boys) from two public high schools in Hubei province were recruited (...) to participate in the three-wave longitudinal study over the span of 1 year during the pandemic (Time 1: November, 2020; Time 2: May, 2021; Time 3: November, 2021). -/- Results: T1 PYD attributes negatively predicted T2 depression and T3 online problematic behaviors. T2 depression positively predicted IGD at T3. T3 IGD significantly predicted greater involvement in T3 CBV, and vice versa. Moreover, depression and one online problem behavior mediated the relationships between PYD attributes and the other online problem behavior, separately and sequentially. (shrink)

This factsheet presents findings from a quantitative study looking at adults’ experiences of sending and sharing potentially harmful digital communications in New Zealand. Typically research into harmful digital communications focuses on the experiences of those on the receiving end – the victims. However, to better address the distress and harm caused, information is needed about the people sending and sharing potentially harmful messages and posts. In this study we asked adult New Zealanders whether they had sent potentially harmful digital communications (...) in the previous year and if so, how often they had done this, who they were sent to, the channel(s) they used, and the reason for doing this. (shrink)

In December 2019 an infectious coronavirus disease, commonly known as COVID-19, was identified in Wuhan, China. The disease spread rapidly and became a global pandemic. New Zealand’s first COVID-19 case was confirmed on 28 February 2020, after which the number of cases began to rise significantly, prompting the New Zealand Government to introduce a nationwide lockdown on 25 March 2020. This factsheet reports early findings from a quantitative study with adult New Zealanders. It explores how prevalent the experiences of unwanted (...) digital communication were in the last 12 months, before, during, and just after the nationwide COVID 19 lockdown. This study found a higher prevalence of unwanted digital communications around the time of the nationwide COVID-19 lockdown. This study’s findings suggest that unexpected health and social events, such as the COVID-19 pandemic and compulsory lockdown, are factors that can trigger changes in people’s experiences of online risk from unwanted digital communications. (shrink)

Research suggests that parents tend to largely underestimate their child’s engagement in risky and/or hurtful behaviours as well as their experiences of harm online. While helpful, the available international evidence is not only limited but also does not reflect the New Zealand context. In addition, understanding parental knowledge of the online experiences of children is important as parents play a critical role in helping their child to prevent or deal with bothering experiences and risky behaviours as well as providing children (...) with emotional support when things go wrong online. To help close the gap of New Zealand-based evidence on the topic, this factsheet presents findings from a quantitative study conducted with New Zealand parents and their children. The objectives of the study are to measure parental knowledge of children’s experiences of risks and harm online, and to compare parents’ level of awareness with their child’s self-reported experiences. The study found a mismatch between parents’, caregivers’ and whānau awareness and their children’s reports of bothering or upsetting experiences online. (shrink)