TONE: A 3-Tiered ONtology for Emotion analysis

TL;DR

The paper addresses the challenge of cross-domain emotion categorization by introducing TONE, a $3$-Tiered ONtology grounded in Parrott's emotion groups. It presents a semi-automated vocabulary construction pipeline and three automated dependency types (isOppositeOf, isComposedOf, plus-LeadsTo) to connect emotions, implemented in OWL/Protege. The ontology undergoes rigorous evaluation through both human expert judgments and DL-based automatic checks, showing high structural and semantic quality and practical gains in emotion detection and review prediction tasks, with implications for empathetic response generation. Overall, TONE offers a scalable, domain-agnostic emotion knowledge base that can enhance NLP systems requiring nuanced emotion vocabularies and inter-emotion relationships.

Abstract

Emotions have played an important part in many sectors, including psychology, medicine, mental health, computer science, and so on, and categorizing them has proven extremely useful in separating one emotion from another. Emotions can be classified using the following two methods: (1) The supervised method's efficiency is strongly dependent on the size and domain of the data collected. A categorization established using relevant data from one domain may not work well in another. (2) An unsupervised method that uses either domain expertise or a knowledge base of emotion types already exists. Though this second approach provides a suitable and generic categorization of emotions and is cost-effective, the literature doesn't possess a publicly available knowledge base that can be directly applied to any emotion categorization-related task. This pushes us to create a knowledge base that can be used for emotion classification across domains, and ontology is often used for this purpose. In this study, we provide TONE, an emotion-based ontology that effectively creates an emotional hierarchy based on Dr. Gerrod Parrot's group of emotions. In addition to ontology development, we introduce a semi-automated vocabulary construction process to generate a detailed collection of terms for emotions at each tier of the hierarchy. We also demonstrate automated methods for establishing three sorts of dependencies in order to develop linkages between different emotions. Our human and automatic evaluation results show the ontology's quality. Furthermore, we describe three distinct use cases that demonstrate the applicability of our ontology.

Figures (8)

• Figure 1: We show the relationship between different tiers i.e., Primary, Secondary, and Tertiary emotions according to Parrott’s group of emotions.
• Figure 2: We show Parrott's group of emotions consisting of emotions in $3$ different hierarchies.
• Figure 3: We show an example for each dependency used in the ontology.
• Figure 4: We show a snippet of the ontology with the Primary emotion as 'Fear', its Secondary emotions: 'Horror', 'Nervousness' and all their Tertiary emotions alongside their respective definitions and vocabularies.
• Figure 5: We show the results obtained after the Structural Evaluation of our ontology, TONE.