Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

EFO: the Emotion Frame Ontology

Stefano De Giorgis, Aldo Gangemi

TL;DR

The paper addresses the lack of consensus on what constitutes emotion and how to model its diverse aspects by proposing EFO, an OWL frame-based ontology network aligned with Framester and the DOLCE foundational ontology. EFO represents emotions as semantic frames with configurable frame elements, enabling joint modeling of multiple theories (e.g., Ekman’s Basic Emotions) and multimodal data. It introduces the EmoCore core, a BE module for Ekman’s theory, and a BE triggers component, and demonstrates automated reasoning with FRED, lexicalization against the Framester hub, and a graph-based emotion detector. The multimodal extension transposes CREMA-D and FER+ datasets into RDF graphs, enabling cross-modal emotion semantics and facilitating more comprehensive affective research with interpretable reasoning on physiological, behavioral, and perceptual data.

Abstract

Emotions are a subject of intense debate in various disciplines. Despite the proliferation of theories and definitions, there is still no consensus on what emotions are, and how to model the different concepts involved when we talk about - or categorize - them. In this paper, we propose an OWL frame-based ontology of emotions: the Emotion Frames Ontology (EFO). EFO treats emotions as semantic frames, with a set of semantic roles that capture the different aspects of emotional experience. EFO follows pattern-based ontology design, and is aligned to the DOLCE foundational ontology. EFO is used to model multiple emotion theories, which can be cross-linked as modules in an Emotion Ontology Network. In this paper, we exemplify it by modeling Ekman's Basic Emotions (BE) Theory as an EFO-BE module, and demonstrate how to perform automated inferences on the representation of emotion situations. EFO-BE has been evaluated by lexicalizing the BE emotion frames from within the Framester knowledge graph, and implementing a graph-based emotion detector from text. In addition, an EFO integration of multimodal datasets, including emotional speech and emotional face expressions, has been performed to enable further inquiry into crossmodal emotion semantics.

EFO: the Emotion Frame Ontology

TL;DR

The paper addresses the lack of consensus on what constitutes emotion and how to model its diverse aspects by proposing EFO, an OWL frame-based ontology network aligned with Framester and the DOLCE foundational ontology. EFO represents emotions as semantic frames with configurable frame elements, enabling joint modeling of multiple theories (e.g., Ekman’s Basic Emotions) and multimodal data. It introduces the EmoCore core, a BE module for Ekman’s theory, and a BE triggers component, and demonstrates automated reasoning with FRED, lexicalization against the Framester hub, and a graph-based emotion detector. The multimodal extension transposes CREMA-D and FER+ datasets into RDF graphs, enabling cross-modal emotion semantics and facilitating more comprehensive affective research with interpretable reasoning on physiological, behavioral, and perceptual data.

Abstract

Emotions are a subject of intense debate in various disciplines. Despite the proliferation of theories and definitions, there is still no consensus on what emotions are, and how to model the different concepts involved when we talk about - or categorize - them. In this paper, we propose an OWL frame-based ontology of emotions: the Emotion Frames Ontology (EFO). EFO treats emotions as semantic frames, with a set of semantic roles that capture the different aspects of emotional experience. EFO follows pattern-based ontology design, and is aligned to the DOLCE foundational ontology. EFO is used to model multiple emotion theories, which can be cross-linked as modules in an Emotion Ontology Network. In this paper, we exemplify it by modeling Ekman's Basic Emotions (BE) Theory as an EFO-BE module, and demonstrate how to perform automated inferences on the representation of emotion situations. EFO-BE has been evaluated by lexicalizing the BE emotion frames from within the Framester knowledge graph, and implementing a graph-based emotion detector from text. In addition, an EFO integration of multimodal datasets, including emotional speech and emotional face expressions, has been performed to enable further inquiry into crossmodal emotion semantics.
Paper Structure (25 sections, 2 figures, 1 table)

This paper contains 25 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Emotion Ontologies
  4. EmOCA
  5. EmotionsOnto
  6. SOCAM Affective Extension
  7. MFOEM
  8. framECO
  9. WordNet Affect
  10. Emotions theories
  11. Emotion Frame Ontology
  12. Framester Ontology
  13. EmoCore Module
  14. EmoCore Classes
  15. EmoCore Properties
  16. ...and 10 more sections

Figures (2)

  • Figure 1: FRED graph generated from the sentence "Cosplaying properly for the first time on Saturday! Pretty nervous..." showing the localization of the activation of the be:Fear emotion frame on the WordNet synset wn:nervous-adjectivesatellite-1.
  • Figure 2: A sample result obtain via SPARQL querying the FER-kg module. Here some examples of :EmotionSituation, including some facial expressor of emotions with values major than "3". From left to right: fer:0035509 including be:Anger and be:Fear; fer:0014735 including be:Enjoyment and be:Anger; and fer:0030527 including be:Sadness and be:Disgust.