"How Bullying is this Message?": A Psychometric Thermometer for Bullying

Cyberbullying statistics are shocking, the number of affected young people is increasing dramatically with the affordability of mobile technology devices combined with a growing number of social networks. This paper proposes a framework to analyse Tweets with the goal to identify cyberharassment in social networks as an important step to protect people from cyberbullying. The proposed framework incorporates latent or hidden variables with supervised learning to determine potential bullying cases resembling short blogging type texts such as Tweets. It uses the LIWC2007 tool that translates Tweet messages into 67 numeric values, representing 67 word categories. The output vectors are then used as features for four different classifiers implemented in Weka. Tests on all four classifiers delivered encouraging predictive capability of Tweet messages. Overall it was found that the use of numeric psychometric values outperformed the same algorithms using both filtered and unfiltered words as features. The best performing algorithms was Random Forest with an F1-value of 0.947 using psychometric features compared to a value of 0.847 for the same algorithm using words as features.