Cyberbullying Blocker Application for Android

Humiliating and slandering people through Internet existed almost since the beginning of communication through this medium. The introduction of new types of devices connecting to the Internet, such as smartphones and tablet computers further facilitated the process of cyberbullying. To deal with this problem we developed an application for Android smartphones which automatically detects a possible harmful content in text. The application can use one of two methods for detection of harmful messages: a method inspired by a brute force search algorithm applied to language modelling, or 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. First tests showed that both methods are working under the Android environment.