TEII: Think, Explain, Interact and Iterate with Large Language Models to Solve Cross-lingual Emotion Detection

TL;DR

This paper presents TEII, a novel framework leveraging large language models and ensemble methods to improve cross-lingual emotion detection, achieving competitive results in the EXALT shared task.

Contribution

It introduces two new multi-iteration and multi-binary classifier workflows and demonstrates the effectiveness of LLMs and ensemble techniques in multilingual emotion detection.

Findings

LLM-based models perform well on multilingual emotion detection

Ensemble methods improve F1-score over individual models

TEII system ranked second in the EXALT shared task

Abstract

Cross-lingual emotion detection allows us to analyze global trends, public opinion, and social phenomena at scale. We participated in the Explainability of Cross-lingual Emotion Detection (EXALT) shared task, achieving an F1-score of 0.6046 on the evaluation set for the emotion detection sub-task. Our system outperformed the baseline by more than 0.16 F1-score absolute, and ranked second amongst competing systems. We conducted experiments using fine-tuning, zero-shot learning, and few-shot learning for Large Language Model (LLM)-based models as well as embedding-based BiLSTM and KNN for non-LLM-based techniques. Additionally, we introduced two novel methods: the Multi-Iteration Agentic Workflow and the Multi-Binary-Classifier Agentic Workflow. We found that LLM-based approaches provided good performance on multilingual emotion detection. Furthermore, ensembles combining all our experimented models yielded higher F1-scores than any single approach alone.