TeamHerald@CHIPSAL 2026: Hate Speech Detection and Sentiment Analysis of Nepali Memes Using Transformer-based Architectures and Ensemble Learning

Ashish Acharya, Anish Khatiwada, Rohit Khadka, Pragya Aryal


Abstract
The analysis of internet memes in the Nepali language is complicated by frequent code-mixing and a lack of established baseline resources. While memes inherently combine visual and textual elements, this study focuses on a text-centric approach by extracting embedded text using an OCR layer and modeling it with Transformer-based architectures. We evaluate six distinct models and investigate the comparative effectiveness of Hard and Soft Voting ensemble strategies across two tasks: binary hate speech detection and three-class sentiment analysis. Experimental results show that a standalone decoder-only model achieved the highest performance for binary classification, whereas the Soft Voting ensemble performed best for the multi-class sentiment task, yielding a 15.8% relative improvement in Macro F1-score over the strongest standalone baseline. These findings suggest that ensemble strategies behave differently across binary and multi-class tasks, highlighting the importance of selecting aggregation methods suited to the classification objective.
Anthology ID:
2026.chipsal-1.24
Volume:
Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026)
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Kengatharaiyer Sarveswaran, Ashwini Vaidya
Venues:
CHiPSAL | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
244–249
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-chipsal-24
DOI:
10.63317/328gg52ap2qp
Bibkey:
Cite (ACL):
Ashish Acharya, Anish Khatiwada, Rohit Khadka, and Pragya Aryal. 2026. TeamHerald@CHIPSAL 2026: Hate Speech Detection and Sentiment Analysis of Nepali Memes Using Transformer-based Architectures and Ensemble Learning. In Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026), pages 244–249, Palma de Mallorca, Spain. ELRA Language Resources Association (ELRA).
Cite (Informal):
TeamHerald@CHIPSAL 2026: Hate Speech Detection and Sentiment Analysis of Nepali Memes Using Transformer-based Architectures and Ensemble Learning (Acharya et al., CHiPSAL 2026)
Copy Citation: