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

• URL: http://arxiv.org/abs/2507.04708v1
• Date: Mon, 07 Jul 2025 06:59:37 GMT
• Title: Why We Feel What We Feel: Joint Detection of Emotions and Their Opinion Triggers in E-commerce
• Authors: Arnav Attri, Anuj Attri, Pushpak Bhattacharyya, Suman Banerjee, Amey Patil, Muthusamy Chelliah, Nikesh Garera,
• Abstract summary: We propose a novel task unifying Emotion detection and Opinion Trigger extraction.<n>EOT-X is a human-annotated collection of 2,400 reviews with fine-grained emotions and opinion triggers.<n>We present EOT-DETECT, a structured prompting framework with systematic reasoning and self-reflection.
• Score: 34.25698222058424
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models [75.85319609088354]
  Sentient Agent as a Judge (SAGE) is an evaluation framework for large language models.<n>SAGE instantiates a Sentient Agent that simulates human-like emotional changes and inner thoughts during interaction.<n>SAGE provides a principled, scalable and interpretable tool for tracking progress toward genuinely empathetic and socially adept language agents.
  arXiv  Detail & Related papers  (2025-05-01T19:06:10Z)
• Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models [35.24458725308099]
  We propose Emotion Interpretation (EI), focusing on causal factors that drive emotional responses.<n>Unlike traditional emotion recognition, EI tasks require reasoning about triggers instead of mere labeling.<n>We present EIBench, a large-scale benchmark encompassing 1,615 basic EI samples and 50 complex EI samples.
  arXiv  Detail & Related papers  (2025-04-10T07:33:49Z)
• Towards a Generative Approach for Emotion Detection and Reasoning [0.7366405857677227]
  We introduce a novel approach to zero-shot emotion detection and emotional reasoning using large language models. Our paper is the first work on using a generative approach to jointly address the tasks of emotion detection and emotional reasoning for texts.
  arXiv  Detail & Related papers  (2024-08-09T07:20:15Z)
• CauESC: A Causal Aware Model for Emotional Support Conversation [79.4451588204647]
  Existing approaches ignore the emotion causes of the distress. They focus on the seeker's own mental state rather than the emotional dynamics during interaction between speakers. We propose a novel framework CauESC, which firstly recognizes the emotion causes of the distress, as well as the emotion effects triggered by the causes.
  arXiv  Detail & Related papers  (2024-01-31T11:30:24Z)
• A Unified Approach to Emotion Detection and Task-Oriented Dialogue Modeling [0.0]
  User emotion detection is often overlooked in text-based task-oriented dialogue systems. We show that seamlessly unifying ED and TOD modeling brings about mutual benefits.
  arXiv  Detail & Related papers  (2024-01-24T20:17:11Z)
• Language Models (Mostly) Do Not Consider Emotion Triggers When Predicting Emotion [87.18073195745914]
  We investigate how well human-annotated emotion triggers correlate with features deemed salient in their prediction of emotions. Using EmoTrigger, we evaluate the ability of large language models to identify emotion triggers. Our analysis reveals that emotion triggers are largely not considered salient features for emotion prediction models, instead there is intricate interplay between various features and the task of emotion detection.
  arXiv  Detail & Related papers  (2023-11-16T06:20:13Z)
• EmoTwiCS: A Corpus for Modelling Emotion Trajectories in Dutch Customer Service Dialogues on Twitter [9.2878798098526]
  This paper introduces EmoTwiCS, a corpus of 9,489 Dutch customer service dialogues on Twitter that are annotated for emotion trajectories. The term emotion trajectory' refers not only to the fine-grained emotions experienced by customers, but also to the event happening prior to the conversation and the responses made by the human operator.
  arXiv  Detail & Related papers  (2023-10-10T11:31:11Z)
• Dynamic Causal Disentanglement Model for Dialogue Emotion Detection [77.96255121683011]
  We propose a Dynamic Causal Disentanglement Model based on hidden variable separation. This model effectively decomposes the content of dialogues and investigates the temporal accumulation of emotions. Specifically, we propose a dynamic temporal disentanglement model to infer the propagation of utterances and hidden variables.
  arXiv  Detail & Related papers  (2023-09-13T12:58:09Z)
• Unsupervised Extractive Summarization of Emotion Triggers [56.50078267340738]
  We develop new unsupervised learning models that can jointly detect emotions and summarize their triggers. Our best approach, entitled Emotion-Aware Pagerank, incorporates emotion information from external sources combined with a language understanding module.
  arXiv  Detail & Related papers  (2023-06-02T11:07:13Z)
• A Dual-Questioning Attention Network for Emotion-Cause Pair Extraction with Context Awareness [3.5630018935736576]
  We propose a Dual-Questioning Attention Network for emotion-cause pair extraction. Specifically, we question candidate emotions and causes to the context independently through attention networks for a contextual and semantical answer. Empirical results show that our method performs better than baselines in terms of multiple evaluation metrics.
  arXiv  Detail & Related papers  (2021-04-15T03:47:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.