Papers with labeling approach
Integrating Plutchik’s Theory with Mixture of Experts for Enhancing Emotion Classification (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for emotion classification ignore the sentimental aspects of text, resulting in a lack of generalization and sampling bias. |
| Approach: | They propose a method for emotion classification using Plutchik’s Wheel of Emotions theory and a Mixture of Experts architecture to evaluate the effectiveness. |
| Outcome: | The proposed method improves the performance of emotion classification. |
PolitiSky24: U.S. Political Bluesky Dataset with User Stance Labels (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Stance detection is a method of identifying the viewpoint expressed in text toward a specific target, such as a political figure. |
| Approach: | They present a dataset for the 2024 U.S. presidential election that includes 16,044 user-target stance pairs enriched with engagement metadata, interaction graphs, and user posting histories. |
| Outcome: | The proposed dataset comprises 16,044 user-target stance pairs enriched with engagement metadata, interaction graphs, and user posting histories. |