# DENS: A Dataset for Multi-class Emotion Analysis

arXiv: https://arxiv.org/abs/1910.11769 · HTML: https://mlsanity.com/paper/1910.11769/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2019.

## Built on by (most cited first, 17 of 17)

- [Emotion Analysis in NLP: Trends, Gaps and Roadmap for Future Directions](https://mlsanity.com/paper/2403.01222/) (2024)
- [No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages](https://mlsanity.com/paper/2411.03769/) (2024)
- [ArtELingo: A Million Emotion Annotations of WikiArt with Emphasis on Diversity over Language and Culture](https://mlsanity.com/paper/2211.10780/) (2022)
- [Evaluating Subjective Cognitive Appraisals of Emotions from Large Language Models](https://mlsanity.com/paper/2310.14389/) (2023)
- [PyPlutchik: visualising and comparing emotion-annotated corpora](https://mlsanity.com/paper/2105.04295/) (2021)
- [Emotion analysis and detection during COVID-19](https://mlsanity.com/paper/2107.11020/) (2021)
- [Can Third-parties Read Our Emotions?](https://mlsanity.com/paper/2504.18673/) (2025)
- [Language Models (Mostly) Do Not Consider Emotion Triggers When Predicting Emotion](https://mlsanity.com/paper/2311.09602/) (2023)
- [Detecting Inspiring Content on Social Media](https://mlsanity.com/paper/2109.02734/) (2021)
- [Fluent but Unfeeling: The Emotional Blind Spots of Language Models](https://mlsanity.com/paper/2509.09593/) (2025)
- [Computational Storytelling and Emotions: A Survey](https://mlsanity.com/paper/2205.10967/) (2022)
- [Automatic Emotion Modelling in Written Stories](https://mlsanity.com/paper/2212.11382/) (2022)
- [Detecting harassment and defamation in cyberbullying with emotion-adaptive training](https://mlsanity.com/paper/2501.16925/) (2025)
- [Emotion Identification for French in Written Texts: Considering their Modes of Expression as a Step Towards Text Complexity Analysis](https://mlsanity.com/paper/2405.14385/) (2024)
- [Performance Evaluation of Emotion Classification in Japanese Using RoBERTa and DeBERTa](https://mlsanity.com/paper/2505.00013/) (2025)
- [Emotion Entanglement and Bayesian Inference for Multi-Dimensional Emotion Understanding](https://mlsanity.com/paper/2604.00819/) (2026)
- [Busemann energy-based attention for emotion analysis in Poincar'e discs](https://mlsanity.com/paper/2604.06752/) (2026)

## Abstract (arXiv)

We introduce a new dataset for multi-class emotion analysis from long-form narratives in English. The Dataset for Emotions of Narrative Sequences (DENS) was collected from both classic literature available on Project Gutenberg and modern online narratives available on Wattpad, annotated using Amazon Mechanical Turk. A number of statistics and baseline benchmarks are provided for the dataset. Of the tested techniques, we find that the fine-tuning of a pre-trained BERT model achieves the best results, with an average micro-F1 score of 60.4%. Our results show that the dataset provides a novel opportunity in emotion analysis that requires moving beyond existing sentence-level techniques.