In this chapter, the authors present an application for Android smartphones to automatically detect possible harmful content in input text. The developed application is aimed to test in practice the performance of the developed cyberbullying detection methods described in previous chapters. The final goal of the developed application will be to help mitigate the problem of cyberbullying by quickly detecting possibly harmful contents in user's entry and warning the user of the possible negative influence. The test application was prepared to use one of two methods for detection of harmful messages: a method inspired by a brute force search algorithm applied to language modelling and a method which uses seed words from three categories to calculate semantic orientation score SO-PMI-IR and then maximize the relevance of categories to specify harmfulness of a message (both methods were described in previous chapters). First tests showed that both methods are working properly under the Android environment.
TopWith the popularization of mobile devices, the problem of cyberbullying has become more noticeable. Apart from the research in cyberbullying detection described in previous chapters, a number of research teams around the world have attempted to develop practical solutions for detection and mitigation of this problem. However, most of the research is still in a developmental phase and is yet to be fully applied in practice. On the other hand, there have been developed market solutions for the detection and mitigation of online bullying, having a capacity to deal with the problem to some extent. Unfortunately, such solutions are usually based on the simplest methods, which narrows the scope of their applicability. Below we present some of such solutions.
FearNot!
One of the examples of a software with a novel approach is FearNot! (http://sourceforge.net/projects/fearnot/). The authors describe it as “an interactive drama/video game that teaches children strategies to prevent bullying and social exclusion.” The development of this software, which uses psychology-inspired character AI, was supported by EU funded research projects Victec and eCircus. The approach taken by the developers, namely, not to detect and stigmatize cyberbullying behavior, but rather to educate children not to become bullies, does indicate a deep insight in the problem. Unfortunately, the development of the software has stopped in early 2013.
BullyGuardPro
An example of a potentially effective software could be BullyGuardPro (https://www.bullyguard.com/). It is a software aimed at detecting cyberbullying activity around a user allowing her to “effectively respond, diffuse and halt cyberbullying and cyberpredation attacks”. The software was developed by Lynne Edwards and April Kontostathis, who lead a team which as some of the first began the research on cyberbullying detection (Kontostathis et al., 2013). Unfortunately, at the time of writing, no details on the technology used in the software, nor its release date is yet known.