Summary of Modeling Emotional Trajectories in Written Stories Utilizing Transformers and Weakly-supervised Learning, by Lukas Christ et al.
Modeling Emotional Trajectories in Written Stories Utilizing Transformers and Weakly-Supervised Learning
by Lukas Christ, Shahin Amiriparian, Manuel Milling, Ilhan Aslan, Björn W. Schuller
First submitted to arxiv on: 4 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a novel approach to automatically model emotional trajectories in stories, which has been limited to unsupervised dictionary-based methods until now. The researchers introduce continuous valence and arousal labels for an existing dataset of children’s stories originally annotated with discrete emotion categories. They collect additional annotations and fine-tune a DeBERTa model using a weakly supervised learning approach. The best configuration achieves high scores on the test set, demonstrating the effectiveness of their proposed method. A detailed analysis reveals factors such as author, individual story, or section within the story affect the results. This paper contributes to the development of emotional storytelling models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Stories are an important way for humans to connect and share emotions. Researchers have been trying to create machines that can understand and predict the emotions in stories. So far, most methods have used dictionaries to identify emotions. But this approach has limitations. In this study, we introduce a new method to model emotional trajectories in stories using continuous valence and arousal labels. We test our approach on a dataset of children’s stories and achieve good results. Our analysis shows that factors like the author or story section affect the outcome. |
Keywords
» Artificial intelligence » Supervised » Unsupervised
