Development of computational linguistic resources for automated detection of textual cyberbullying threats in Roman Urdu language

Automatic Cyberbullying detection has remained very challenging task since social media content and conversations are usually posted in unstructured free-text form leaving behind the language norms. The major concern gap formulating cyberbullying strategies is scarcity of available linguistic resources typically for newly evolved languages. Roman Urdu recently emerged hence a resource poor language. been widely known as national Pakistan. However, because socio-cultural multilingual aspects, used on Internet by Asians and more specifically Pakistanis. To fulfil above stated gap, this research work presents guidelines data annotation process developed two resources: (i) Annotated corpus Language cyberaggression offensive detection. involved bilingual annotators instead of crowdsourcing. It benefit correctly annotating instances that constitute clear cases cyberbullying without compromising quality. developed highly balanced (with almost negligible skew) unlike most existing corpuses even mature (ii) Processing textual information NLP tasks involves Stop-word elimination sub phase. Stop words carry least semantic increase feature space compared to other tokens index terms corpora. We have domain specific stop considering all lexical variants context aggression collected data. been carried out using python programming Pycharm IDE.