Hybrid Approach to Explain BERT Model: Sentiment Analysis Case

Aroua Hedhili, Aroua Hedhili, Islem Bouallagui, Islem Bouallagui

2024

Abstract

The increasing use of Artificial Intelligence (AI), particularly Deep Neural Networks (DNNs), has raised concerns about the opacity of these ’black box’ models in decision-making processes. Explainable AI (XAI) has emerged to address this issue by making AI systems more understandable and trustworthy through various techniques. In this research paper, we deal with a new approach to explain model combining counterfactual explanations and domain knowledge visualization. Our contribution explores how domain knowledge, guided by expert decision-makers, can improve the effectiveness of counterfactual explanations. Additionally, the presented research underscores the significance of collecting user feedback to create a human-centered approach. Our experiments were conducted on a BERT model for sentiment analysis on IMDB movie reviews dataset.

Paper Citation

in Harvard Style

Hedhili A. and Bouallagui I. (2024). Hybrid Approach to Explain BERT Model: Sentiment Analysis Case. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 251-259. DOI: 10.5220/0012318400003636

in Bibtex Style

@conference{icaart24,
author={Aroua Hedhili and Islem Bouallagui},
title={Hybrid Approach to Explain BERT Model: Sentiment Analysis Case},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={251-259},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012318400003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Hybrid Approach to Explain BERT Model: Sentiment Analysis Case
SN - 978-989-758-680-4
AU - Hedhili A.
AU - Bouallagui I.
PY - 2024
SP - 251
EP - 259
DO - 10.5220/0012318400003636
PB - SciTePress