SubmissionNumber#=%=#30
FinalPaperTitle#=%=#VRLLab at HSD-2Lang 2024: Turkish Hate Speech Detection Online with TurkishBERTweet
ShortPaperTitle#=%=#
NumberOfPages#=%=#
CopyrightSigned#=%=#
JobTitle#==#
Organization#==#
Abstract#==#Social media platforms like Twitter - recently rebranded as X - produce nearly half a billion tweets daily and host a significant number of users that can be affected by content that are not properly moderated. In this work, we present an approach that ranked third at the \texttt{HSD-2Lang 2024} competition's subtask-A along with additional methodology developed for this task and evaluation of different approaches. We utilize three different models and the best performing approach use publicly-available TurkishBERTweet model with low-rank adaptation (LoRA) for fine tuning. We also experiment with another publicly available model and a novel methodology to ensemble different hand-crafted features and outcomes of different models. Finally, we report the experimental results, competition scores, and discussion to improve this effort further.
Author{1}{Firstname}#=%=#Ali
Author{1}{Lastname}#=%=#Najafi
Author{1}{Email}#=%=#ali.najafi@sabanciuniv.edu
Author{1}{Affiliation}#=%=#Sabanci University
Author{2}{Firstname}#=%=#Onur
Author{2}{Lastname}#=%=#Varol
Author{2}{Username}#=%=#onurvarol
Author{2}{Email}#=%=#onur.varol@sabanciuniv.edu
Author{2}{Affiliation}#=%=#Sabanci University

==========
èéáğö