ScalarLab@TRAC2024: Exploring Machine Learning Techniques for Identifying Potential Offline Harm in Multilingual Commentaries

Simple item page
dc.contributor.authorAnagha, H.C.
dc.contributor.authorKrishna, S.M.
dc.contributor.authorJha, S.S.
dc.contributor.authorRao, V.T.
dc.contributor.authorAnand Kumar, M.
dc.date.accessioned2026-02-06T06:34:06Z
dc.date.issued2024
dc.description.abstractThe objective of the shared task, Offline Harm Potential Identification (HarmPot-ID), is to build models to predict the offline harm potential of social media texts. "Harm potential" is defined as the ability of an online post or comment to incite offline physical harm such as murder, arson, riot, rape, etc. The first subtask was to predict the level of harm potential, and the second was to identify the group to which this harm was directed towards. This paper details our submissions for the shared task that includes a cascaded SVM model, an XGBoost model, and a TF-IDF weighted Word2Vec embedding-supported SVM model. Our system ranked 4th in the first subtask and 3rd in the second. Several other models that were explored have also been detailed. © 2024 ELRA Language Resource Association.
dc.identifier.citationTRAC 2024: 4th Workshop on Threat, Aggression and Cyberbullying at LREC-COLING 2024 - Workshop Proceedings, 2024, Vol., , p. 32-36
dc.identifier.urihttps://doi.org/
dc.identifier.urihttps://idr.nitk.ac.in/handle/123456789/29055
dc.publisherEuropean Language Resources Association (ELRA)
dc.subjectHarm Potential
dc.subjectHarmPot
dc.subjectOffline harm
dc.subjectOffline Harm
dc.subjectText classification
dc.subjectTF-IDF
dc.subjectweighted word embeddings
dc.titleScalarLab@TRAC2024: Exploring Machine Learning Techniques for Identifying Potential Offline Harm in Multilingual Commentaries

Files

Collections

Conference Papers