Predicting the type and target of offensive social media posts in Marathi

Abstract

The presence of offensive language on social media is very common motivating platforms to invest in strategies to make communities safer. This includes developing robust machine learning systems capable of recognizing offensive content online. Apart from a few notable exceptions, most research on automatic offensive language identification has dealt with English and a few other high resource languages such as French, German, and Spanish. In this paper we address this gap by tackling offensive language identification in Marathi, a lowresource Indo-Aryan language spoken in India. We introduce the Marathi Offensive Language Dataset v.2.0 or MOLD 2.0 and present multiple experiments on this dataset. MOLD 2.0 is a much larger version of MOLD with expanded annotation to the levels B (type) and C (target) of the popular OLID taxonomy.MOLD 2.0 is the first hierarchical offensive language dataset compiled for Marathi, thus opening new avenues for research in low-resource Indo-Aryan languages. Finally, we also introduce SeMOLD, a larger dataset annotated following the semi-supervised methods presented in SOLID [1].

Offensive Language Identification in Transliterated and Code-Mixed Bangla

“…We adopt the guidelines introduced by the popular OLID annotation taxonomy (Zampieri et al, 2019a) used in the OffensEval shared task (Zampieri et al, 2019b) and replicated in multiple other datasets in languages such as Danish (Sigurbergsson and Derczynski, 2020), Greek (Pitenis et al, 2020), Marathi (Gaikwad et al, 2021;Zampieri et al, 2022), Portuguese (Sigurbergsson and Derczynski, 2020), Sinhala (Ranasinghe et al, 2022) and Turkish (Çöltekin, 2020). We choose OLID due to the flexibility provided by its threelevel hierarchical taxonomy that allows us to model different types of offensive and abusive content (e.g., hate speech, cyberbulling, etc.)…”