Witcherses at SemEval-2023 Task 12: Ensemble Learning for African Sentiment Analysis

Monil Gokani, K V Aditya Srivatsa, Radhika Mamidi

Abstract
This paper describes our system submission for SemEval-2023 Task 12 AfriSenti-SemEval: Sentiment Analysis for African Languages. We propose an XGBoost-based ensemble model trained on emoticon frequency-based features and the predictions of several statistical models such as SVMs, Logistic Regression, Random Forests, and BERT-based pre-trained language models such as AfriBERTa and AfroXLMR. We also report results from additional experiments not in the system. Our system achieves a mixed bag of results, achieving a best rank of 7th in three of the languages - Igbo, Twi, and Yoruba.
Anthology ID:
2023.semeval-1.48
Volume:
Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023)
Month:
July
Year:
2023
Address:
Toronto, Canada
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
357–364
Language:
URL:
https://aclanthology.org/2023.semeval-1.48
DOI:
Bibkey:
Cite (ACL):
Monil Gokani, K V Aditya Srivatsa, and Radhika Mamidi. 2023. Witcherses at SemEval-2023 Task 12: Ensemble Learning for African Sentiment Analysis. In Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 357–364, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Witcherses at SemEval-2023 Task 12: Ensemble Learning for African Sentiment Analysis (Gokani et al., SemEval 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nodalida-main-page/2023.semeval-1.48.pdf
PDF Search