Lost in “Transl-Hation”: Exploring the Impact of Machine Translation as an Intermediary Tool in Detecting Armenian Hate Speech

Abstract

As the pervasive spread of hate speech continues to pose significant challenges to online communities, detecting, and countering hateful content on social media has become a priority. Social media platforms typically use machine translation to identify the hateful content of the posts made in languages other than English. If this approach works effectively in identifying explicit hateful content in languages that are predominantly used on social media, its effect is almost insignificant when it comes to Armenian. The present research investigates the effectiveness of machine translation as an intermediary tool in accurately identifying and addressing instances of Armenian hate speech posts retrieved from social networking websites. The study of hate speech posts and comments made by Armenian users in Armenian helps identify that it is often the absence of intricate cultural and linguistic nuances, as well as insufficient contextualized understanding, that impede with hate speech detection in Armenian.