Cyberbullying Prevention

Sarah G

EME 2040- 003

Dr. James Hatten

October 2^nd, 2018

Annotation #6

Source Reference

Van Hee, C., Jacobs, G., Emmery, C., Desmet, B., Lefever, E., Verhoeven, B., … Hoste, V. (2018). Automatic detection of cyberbullying in social media text. PLoS ONE, 13(10), 1–22. https://doi-org.ezproxy.lib.usf.edu/10.1371/journal.pone.0203794

Article Type

An online published article detailing the impact of cyberbullying and prevention methods.

First Citation

“ “ (Van H et al. 2018).

Brief Summary

The article focused on both the causes of bullying, its effects and preventative measures. The article went on to describe the preventative measures already in place along with an evaluation of their effectiveness. Further along in the article, a description was provided of proposed measures to be taken to counteract cyberbullying.

Summary

The concept of bullying was introduced along with the form of cyberbullying. The authors differentiated between explaining the history of bullying being in person and ever existent while noting the recentness of the rise of cyberbullying. Cyberbullying was noted to be more dangerous in its ability to follow a person home

Furthermore, the authors described the positives of social media along with the negatives.

Positives: communication made available anywhere anytime, engage in social interactions, establish new relationships, maintain old friendships

Negatives: increases the risk of children being confronted by threatening situations (grooming, sexually transgressive behavior, signals of depression and suicidal thoughts, and cyberbullying), reachable 24/7, anonymous, convenience for bullies

Beyond this, the authors went on to detail that Belgium is one of the places where the government has stepped in to provide an online initiative to prevent cyberbullying and its effects by providing help lines and online safety information for the public.

Following this description, the authors noted that they did not feel that this program was as effective as it could have been. The reason for this was because of the statistics that followed describing that 72% of teens were reported having been bullying online.

The authors went on to suggest the following ways to limit cyberbullying:

• Effective monitoring of online content
• Intelligent systems to identify potential threats
• Promotion of parental control tools to block undesirable content
• Machine learning method based on a linear SVM classifier exploiting a rich feature set

Significant Quotes

• Accessibility of predators to children can become a form of cyberbullying

“On the negative side however, social media increase the risk of children being confronted with threatening situations including grooming or sexually transgressive behaviour, signals of depression and suicidal thoughts, and cyberbullying. Users are reachable 24/7 and are often able to remain anonymous if desired: this makes social media a convenient way for bullies to target their victims outside the school yard” (Van H et al. p2).

• These rates of cyberbullying indicate preventative measures are inneffective

“In spite of these efforts, a lot of undesirable and hurtful content remains online. [2] analysed a body of quantitative research on cyberbullying and observed cybervictimisation rates among teenagers between 20% and 40%. [5] focused on 12 to 17 year olds living in the United States and found that no less than 72% of them had encountered cyberbullying at least once within the year preceding the questionnaire” (Van H et al. p2).

• Proposed solution is a detection program for cyberbullying

“Successful detection depends on effective monitoring of online content, but the amount of information on the Web makes it practically unfeasible for moderators to monitor all user-generated content manually. To tackle this problem, intelligent systems are required that process this information in a fast way and automatically signal potential threats. This way, moderators can respond quickly and prevent threatening situations from escalating” (Van H et al. p2).

• Parental controls are recommended to shield children from some forms of harm

“Parental control tools (e.g. NetNanny, https://www.netnanny.com/) already block unsuited or undesirable content and some social networks make use of keyword-based moderation tools (i.e. using lists of profane and insulting words to flag harmful content). However, such approaches typically fail to detect implicit and subtle forms of cyberbullying in which no explicit vocabulary is used. This creates the need for intelligent and self-learning systems that go beyond keyword spotting and hence improve the recall of cyberbullying detection” (Van H et al. p2).

Evaluation

Strengths: The authors did a good job at organizing the articles layout and content

Weaknesses: The authors did not mention explicitly where some of their statistics came from