Prompt Distillation for Emotion Analysis

Andrew Mackey, Susan Gauch, Israel Cuevas

2024

Abstract

Emotion Analysis (EA) is a field of study closely aligned with sentiment analysis whereby a discrete set of emotions are extracted from a given document. Existing methods of EA have traditionally explored both lexicon and machine learning techniques for this task. Recent advancements in large language models have achieved success in a wide range of tasks, including language, images, speech, and videos. In this work, we construct a model that applies knowledge distillation techniques to extract information from a large language model which instructs a lightweight student model to improve its performance with the EA task. Specifically, the teacher model, which is much larger in terms of parameters and training inputs, performs an analysis of the document and shares this information with the student model to predict the target emotions for a given document. Experimental results demonstrate the efficacy of our proposed prompt-based knowledge distillation approach for EA.

Paper Citation

in Harvard Style

Mackey A., Gauch S. and Cuevas I. (2024). Prompt Distillation for Emotion Analysis. In Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR; ISBN 978-989-758-716-0, SciTePress, pages 328-334. DOI: 10.5220/0012951200003838

in Bibtex Style

@conference{kdir24,
author={Andrew Mackey and Susan Gauch and Israel Cuevas},
title={Prompt Distillation for Emotion Analysis},
booktitle={Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR},
year={2024},
pages={328-334},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012951200003838},
isbn={978-989-758-716-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR
TI - Prompt Distillation for Emotion Analysis
SN - 978-989-758-716-0
AU - Mackey A.
AU - Gauch S.
AU - Cuevas I.
PY - 2024
SP - 328
EP - 334
DO - 10.5220/0012951200003838
PB - SciTePress