• International Journal of Computer Science & Network Security
• /
• v.23 no.5
• /
• pp.1-6
• /
• 2023

Text mining (TM) is most widely used to process the various unstructured text documents and process the data present in the various domains. The other name for text mining is text classification. This domain is most popular in many domains such as movie reviews, product reviews on various E-commerce websites, sentiment analysis, topic modeling and cyber bullying on social media messages. Cyber-bullying is the type of abusing someone with the insulting language. Personal abusing, sexual harassment, other types of abusing come under cyber-bullying. Several existing systems are developed to detect the bullying words based on their situation in the social networking sites (SNS). SNS becomes platform for bully someone. In this paper, An Enhanced text mining approach is developed by using Ensemble Algorithm (ETMA) to solve several problems in traditional algorithms and improve the accuracy, processing time and quality of the result. ETMA is the algorithm used to analyze the bullying text within the social networking sites (SNS) such as facebook, twitter etc. The ETMA is applied on synthetic dataset collected from various data a source which consists of 5k messages belongs to bullying and non-bullying. The performance is analyzed by showing Precision, Recall, F1-Score and Accuracy.

• The Journal of Korean Association of Computer Education
• /
• v.18 no.2
• /
• pp.59-70
• /
• 2015

This paper aims at developing a valid evaluation tool which has reliability to measure the tendency of cyber bullying that is on the increase recently. After setting up the concept of cyber bullying and exploring its factors by reference to advanced research, we developed the draft tool through modifying by the expert group. By conducting several surveys using this evaluation tool, we have verified the reliability and validity of our tool. And we also have developed an evaluation tool to measure its tendency. As a result, the complementary evaluation tool of cyber-bullying tendency was proposed with more advanced and accurate test.

• Informatization Policy
• /
• v.26 no.2
• /
• pp.46-61
• /
• 2019

This study constructs an integrated model for university students' smart phone cyber bullying and tests interaction effects between causal and control factors. Causal factors include low self-control, differential association with cyber bullying peers, and victimization experiences; and control factors include internet ethics, perceived certainty of formal punishment, and bond to parents. This study focuses on examining how internet ethics buffers the effect of causal factors in cyber bullying. Results show that both differential association with cyber bullying peers and victimization experiences have significant effects on cyber bullying. And among the control factors, internet ethics only has a negative direct effect on cyber bullying. In addition, it is found that there are significant interaction effects between two causal factors - differential association with cyber bullying peers and victimization experiences - and internet ethics. It is also shown that there is a significant interaction effect between victimization experience and bond to parents, but a perceived formal punishment has no significant control effect. It is revealed that internet ethics is a main control factor in buffering the effects of causal factors in cyber bullying.

• Journal of Information Technology Services
• /
• v.14 no.1
• /
• pp.175-194
• /
• 2015

As the explosive growth of SNS users, SNS affects every aspect of our lives. Beyond the individual's scope there is a powerful influence in society. Now cyber bullying is a big problem of this society. To analyze the relationship between the SNS user features and cyber bullying phenomenon, various SNS user's personal and social characteristics were set to variables affecting the cyber bullying phenomenon on the SNS. For the research, questionnaire survey was conducted for total 200 subjects among 10~60 age band in each region across the country. We set a research model including the items that are found to be affected in cyber bullying through the prior researches. To analyze interrelation of cyber bullying phenomenon and the general characteristics of SNS users, multiple regression analysis and other analyses were conducted. As a statistical result, we found the correlation among variables and the suggestion points for a SNS platform development direction.

• Journal of muscle and joint health
• /
• v.25 no.3
• /
• pp.218-229
• /
• 2018

Purpose: The purpose of this study is to investigate relationships among workplace face to face bullying, cyber bullying, self-esteem, and turnover intention of hospital nurses, and to identify affecting factors for turnover intention through their relationships. Methods: Data were collected from 178 hospital nurses by self-reported questionnaire. The relationship among variables were analyzed with Pearson's coefficient correlation and affecting factors for turnover intention were identified by using multiple linear regression. Results: The mean score of turnover intention was $3.55{\pm}0.94$. Turnover intention was significantly different by age, marriage status, educational background, total experience as a nurse, designation, health status, bullying experience, and bullied experience. Turnover intention had positive relationships with workplace face to face bullying and hospital size, but negative relationships with self-esteem and health status. Workplace face to face bullying, health status and hospital size were identified as influencing factors in turnover intention. Conclusion: It is necessary to nursing community's efforts to decrease face to face bullying in order to lower the turnover intention of nurses. In this regard workplace bullying among nurses should be addressed using a comprehensive strategy that considers both individual and organizational factors. It is also necessary to nurse 's efforts to increase self-esteem.

• The Journal of Bigdata
• /
• v.1 no.1
• /
• pp.67-75
• /
• 2016

The study analyzed big data extracted from Google and social media to identify factors related to searches on cyber bullying in Korea and America. Korea's cyber bullying analysis was conducted social big data collected from online news sites, blogs, $caf{\acute{e}}s$, social network services and message for between January 1, 2011 and March 31, 2013. Google search trends for the search words of stress, exercise, drinking, and cyber bullying were obtained for January 1, 2004 and December 22, 2013. The main results of this study were as follows: first, the significant factors stress were cyber bullying that Korea more than America. Secondly, a positive relationship was found between stress and drinking, exercise and cyber bullying both Korea and America. Thirdly, significant differences were found all path both Korea and America. The study shows that both adults and teenagers are influenced in Korea. We need to develop online application that if cyber bullying behavior was predicted can intervene in real time because these actual cyber bullying-related exposure to psychological and behavioral characteristic.

• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.59-66
• /
• 2023

Text mining (TM) is most widely used to find patterns from various text documents. Cyber-bullying is the term that is used to abuse a person online or offline platform. Nowadays cyber-bullying becomes more dangerous to people who are using social networking sites (SNS). Cyber-bullying is of many types such as text messaging, morphed images, morphed videos, etc. It is a very difficult task to prevent this type of abuse of the person in online SNS. Finding accurate text mining patterns gives better results in detecting cyber-bullying on any platform. Cyber-bullying is developed with the online SNS to send defamatory statements or orally bully other persons or by using the online platform to abuse in front of SNS users. Deep Learning (DL) is one of the significant domains which are used to extract and learn the quality features dynamically from the low-level text inclusions. In this scenario, Convolutional neural networks (CNN) are used for training the text data, images, and videos. CNN is a very powerful approach to training on these types of data and achieved better text classification. In this paper, an Ensemble model is introduced with the integration of Term Frequency (TF)-Inverse document frequency (IDF) and Deep Neural Network (DNN) with advanced feature-extracting techniques to classify the bullying text, images, and videos. The proposed approach also focused on reducing the training time and memory usage which helps the classification improvement.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.6
• /
• pp.499-506
• /
• 2021

The purpose of this study is to verify the effect of SNS addiction on cyber-bullying among adolescents, considering the adjustment effect of friendship on this relationship. This study involved 811 middle/high school students with a gender distribution of 391 males and 420 females. According to the analysis, the higher the level of SNS addiction, the higher the level of cyber-bullying. A hierarchical regression analysis was conducted to verify the moderating effect of friendship. The result shows that better peer communication and reliance lowers the impact of cyber-bullying from SNS addiction. Based on research results suggesting the popularization of proactive pre-diagnosis programs to solve SNS addiction, practical intervention plans and the limitations of research on SNS addiction and cyber-bullying in youth are suggested.

• The Journal of the Korea Contents Association
• /
• v.16 no.1
• /
• pp.256-262
• /
• 2016

A cyber crime has been evolving, as other crimes have. Beyond physical damages such as financial crimes in the cyber world, it has evolved into psychological forms like cyber-bullying. In today's crimes, measures that consider psychological effects of crimes are highly regarded in that fear of crime is considered as well as visible crimes. Accordingly, cyber bullying, which causes psychological damages, needs to be treated very importantly. Because the characteristics of cyber crime is caused by different circumstances from the real world, measures should be taken in different aspects. Rather than physical damages, which can be found in the conventional crimes, cyber crimes cause psychological damages, so the effect that has on inflicting should be specified. Especially, in the environment that virtual reality is ubiquitous through smart phones, it is very difficult to establish measures by considering all the causes of general cyber crimes. Therefore, this study estimated what affects cyber bullying by focusing on personalized faith factor among social bond theory, which can control cyber crimes. As a result, self-controling faith was verified to have a negative effect on cyber bullying, so faith is a very important factor in personalized environment. Thus, it is suggested that the characteristics of cyber space and education of humanism, which can affect individuals' faith should be emphasized.

• Journal of Korea Game Society
• /
• v.20 no.2
• /
• pp.45-60
• /
• 2020

Cyber bullying is increasing these days and becoming a serious social problem that gives rise to issues such as school violence and cyber crimes. We had developed a serious game-based education program for teenagers who are familiar with computer games. After pilot test the educational effect was also found to be high. I have found the followings in this case study. Serious game is effective media for cyber bullying prevention education. Second, cooperation between content experts and game development experts is essential to develop educational games.