Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Proxy-Based Method for Mapping Discrete Emotions onto VAD model

Michal R. Wrobel

TL;DR

The paper addresses the problem of linking discrete emotion labels with the continuous Valence-Arousal-Dominance ($V$,$A$,$D$) space and proposes a proxy-based, human-centric method using user-generated geometric animations as intermediaries. It implements a two-phase process where participants first encode an emotion as an animation and then assess that animation along the $V$,$A$,$D$ dimensions, validated through two iterative studies. The combined data yield a comprehensive, robust mapping of ten discrete emotions onto the $V$,$A$,$D$ space, supported by a sensitivity analysis that confirms stability across outliers. This work enables practical harmonization of heterogeneous affective datasets and offers a generalizable approach for embedding qualitative emotion labels into quantitative, multimodal representations for AI systems.

Abstract

Mapping discrete and dimensional models of emotion remains a persistent challenge in affective science and computing. This incompatibility hinders the combination of valuable data sets, creating a significant bottleneck for training robust machine learning models. To bridge this gap, this paper presents a novel, human-centric, proxy-based approach that transcends purely computational or direct mapping techniques. Implemented through a web-based survey, the method utilizes simple, user-generated geometric animations as intermediary artifacts to establish a correspondence between discrete emotion labels and the continuous valence-arousal-dominance (VAD) space. The approach involves a two-phase process: first, each participant creates an animation to represent a given emotion label (encoding); then, they immediately assess their own creation on the three VAD dimensions. The method was empirically validated and refined through two iterative user studies. The results confirmed the method's robustness. Combining the data from both studies generated a final, comprehensive mapping between discrete and dimensional models.

A Proxy-Based Method for Mapping Discrete Emotions onto VAD model

TL;DR

The paper addresses the problem of linking discrete emotion labels with the continuous Valence-Arousal-Dominance (,,) space and proposes a proxy-based, human-centric method using user-generated geometric animations as intermediaries. It implements a two-phase process where participants first encode an emotion as an animation and then assess that animation along the ,, dimensions, validated through two iterative studies. The combined data yield a comprehensive, robust mapping of ten discrete emotions onto the ,, space, supported by a sensitivity analysis that confirms stability across outliers. This work enables practical harmonization of heterogeneous affective datasets and offers a generalizable approach for embedding qualitative emotion labels into quantitative, multimodal representations for AI systems.

Abstract

Mapping discrete and dimensional models of emotion remains a persistent challenge in affective science and computing. This incompatibility hinders the combination of valuable data sets, creating a significant bottleneck for training robust machine learning models. To bridge this gap, this paper presents a novel, human-centric, proxy-based approach that transcends purely computational or direct mapping techniques. Implemented through a web-based survey, the method utilizes simple, user-generated geometric animations as intermediary artifacts to establish a correspondence between discrete emotion labels and the continuous valence-arousal-dominance (VAD) space. The approach involves a two-phase process: first, each participant creates an animation to represent a given emotion label (encoding); then, they immediately assess their own creation on the three VAD dimensions. The method was empirically validated and refined through two iterative user studies. The results confirmed the method's robustness. Combining the data from both studies generated a final, comprehensive mapping between discrete and dimensional models.

Paper Structure

This paper contains 10 sections, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. The Proxy-Based Mapping Method
  4. User Studies: An Iterative Approach to Validation and Mapping
  5. Study 1: Initial Validation
  6. Study 2: Replication and Refinement
  7. Final Emotion Mapping
  8. Discussion
  9. Limitations and Future Work
  10. Conclusions

Figures (3)

  • Figure 1: Sample screens from Study 1 web-based questionnaire
  • Figure 2: Study 2 web-based questionnaire
  • Figure 3: Visualization of mapping between discrete emotions and VAD in 3D space