Exploiting Large Language Models for Enhanced Review Classification Explanations Through Interpretable and Multidimensional Analysis

Cosentino C., GÜNDÜZ CÜRE M., Marozzo F., ÖZTÜRK BİRİM Ş.

27th International Conference on Discovery Science, DS 2024, Pisa, İtalya, 14 - 16 Ekim 2024, cilt.15243 LNAI, ss.3-18, (Tam Metin Bildiri)

Yayın Türü: Bildiri / Tam Metin Bildiri
Cilt numarası: 15243 LNAI
Doi Numarası: 10.1007/978-3-031-78977-9_1
Basıldığı Şehir: Pisa
Basıldığı Ülke: İtalya
Sayfa Sayıları: ss.3-18
Anahtar Kelimeler: Large Language Models, Natural Language Processing, BERT, GPT, ChatGPT, Interpretable Models, Explainability
Manisa Celal Bayar Üniversitesi Adresli: Evet

Özet

In today’s digital world, user-generated reviews play a pivotal role across diverse industries, providing invaluable insights into consumer experiences, preferences, and concerns. These reviews heavily influence the strategic decisions of businesses. Advanced machine learning techniques, including Large Language Models (LLMs) like BERT and GPT, have greatly facilitated the analysis of this vast amount of unstructured data, enabling the extraction of actionable insights. However, while achieving high classification accuracy is crucial, the demand for explainability has gained prominence. It is essential to comprehend the reasoning behind classification decisions to effectively utilize user-generated content analytics. This paper presents a methodology that leverages interpretable and multidimensional classification to generate explanations from user reviews. Compared to basic explanations readily available through systems like Chat-GPT, our methodology delves deeper into the classification of reviews across various dimensions (such as sentiment, emotion, and topics addressed) to produce more comprehensive explanations for user review classifications. Experimental results demonstrate the precision of our methodology in explaining why a particular review was classified in a specific manner.