Why We Feel What We Feel: Joint Detection of Emotions and Their Opinion Triggers in E-commerce

TL;DR

This paper introduces a joint task for detecting emotions and their opinion triggers in e-commerce reviews, along with a new dataset and a structured prompting framework for large language models, improving understanding of customer emotional responses.

Contribution

It proposes a novel joint task unifying emotion detection and opinion trigger extraction, introduces the EOT-X dataset, and develops EOT-DETECT, a structured prompting framework for LLMs that outperforms existing methods.

Findings

EOT-DETECT surpasses zero-shot and chain-of-thought methods.

EOT-X provides a new annotated dataset for emotion and trigger detection.

The joint task enhances understanding of customer emotional responses in reviews.

Abstract

Customer reviews on e-commerce platforms capture critical affective signals that drive purchasing decisions. However, no existing research has explored the joint task of emotion detection and explanatory span identification in e-commerce reviews - a crucial gap in understanding what triggers customer emotional responses. To bridge this gap, we propose a novel joint task unifying Emotion detection and Opinion Trigger extraction (EOT), which explicitly models the relationship between causal text spans (opinion triggers) and affective dimensions (emotion categories) grounded in Plutchik's theory of 8 primary emotions. In the absence of labeled data, we introduce EOT-X, a human-annotated collection of 2,400 reviews with fine-grained emotions and opinion triggers. We evaluate 23 Large Language Models (LLMs) and present EOT-DETECT, a structured prompting framework with systematic reasoning and self-reflection. Our framework surpasses zero-shot and chain-of-thought techniques, across e-commerce domains.