# Experiencers, Stimuli, or Targets: Which Semantic Roles Enable Machine Learning to Infer the Emotions?

arXiv: https://arxiv.org/abs/2011.01599 · HTML: https://mlsanity.com/paper/2011.01599/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Nov 2020.

## Built on by (most cited first, 5 of 5)

- [Multi-Task Learning and Adapted Knowledge Models for Emotion-Cause Extraction](https://mlsanity.com/paper/2106.09790/) (2021)
- [x-enVENT: A Corpus of Event Descriptions with Experiencer-specific Emotion and Appraisal Annotations](https://mlsanity.com/paper/2203.10909/) (2022)
- [Where are We in Event-centric Emotion Analysis? Bridging Emotion Role Labeling and Appraisal-based Approaches](https://mlsanity.com/paper/2309.02092/) (2023)
- [Improving Language Models for Emotion Analysis: Insights from Cognitive Science](https://mlsanity.com/paper/2406.10265/) (2024)
- [Fear Is Not Always Fear: Variation in Emotion Label Equivalence Across Datasets](https://mlsanity.com/paper/2610.12841/) (2026)

## Abstract (arXiv)

Emotion recognition is predominantly formulated as text classification in which textual units are assigned to an emotion from a predefined inventory (e.g., fear, joy, anger, disgust, sadness, surprise, trust, anticipation). More recently, semantic role labeling approaches have been developed to extract structures from the text to answer questions like: "who is described to feel the emotion?" (experiencer), "what causes this emotion?" (stimulus), and at which entity is it directed?" (target). Though it has been shown that jointly modeling stimulus and emotion category prediction is beneficial for both subtasks, it remains unclear which of these semantic roles enables a classifier to infer the emotion. Is it the experiencer, because the identity of a person is biased towards a particular emotion (X is always happy)? Is it a particular target (everybody loves X) or a stimulus (doing X makes everybody sad)? We answer these questions by training emotion classification models on five available datasets annotated with at least one semantic role by masking the fillers of these roles in the text in a controlled manner and find that across multiple corpora, stimuli and targets carry emotion information, while the experiencer might be considered a confounder. Further, we analyze if informing the model about the position of the role improves the classification decision. Particularly on literature corpora we find that the role information improves the emotion classification.