# Modeling Emotional Trajectories in Written Stories Utilizing Transformers and Weakly-Supervised Learning

arXiv: https://arxiv.org/abs/2406.02251 · HTML: https://mlsanity.com/paper/2406.02251/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 60 references that are in the map.
- First posted on arXiv 4 Jun 2024.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Dawn of the transformer era in speech emotion recognition: closing the valence gap](https://mlsanity.com/paper/2203.07378/) (2022)
- [AVEC 2019 Workshop and Challenge: State-of-Mind, Detecting Depression with AI, and Cross-Cultural Affect Recognition](https://mlsanity.com/paper/1907.11510/) (2019)
- [The emotional arcs of stories are dominated by six basic shapes](https://mlsanity.com/paper/1606.07772/) (2016)
- [SEWA DB: A Rich Database for Audio-Visual Emotion and Sentiment Research in the Wild](https://mlsanity.com/paper/1901.02839/) (2019)
- [PySBD: Pragmatic Sentence Boundary Disambiguation](https://mlsanity.com/paper/2010.09657/) (2020)
- [An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era](https://mlsanity.com/paper/2210.03538/) (2022)
- [Leveraging Recent Advances in Deep Learning for Audio-Visual Emotion Recognition](https://mlsanity.com/paper/2103.09154/) (2021)
- [The MuSe 2021 Multimodal Sentiment Analysis Challenge: Sentiment, Emotion, Physiological-Emotion, and Stress](https://mlsanity.com/paper/2104.07123/) (2021)
- [Dimensional Emotion Detection from Categorical Emotion](https://mlsanity.com/paper/1911.02499/) (2019)
- [The MuSe 2022 Multimodal Sentiment Analysis Challenge: Humor, Emotional Reactions, and Stress](https://mlsanity.com/paper/2207.05691/) (2022)
- [Modeling emotion in complex stories: the Stanford Emotional Narratives Dataset](https://mlsanity.com/paper/1912.05008/) (2019)
- [EmoNet: A Transfer Learning Framework for Multi-Corpus Speech Emotion Recognition](https://mlsanity.com/paper/2103.08310/) (2021)
- [A Survey on Sentiment and Emotion Analysis for Computational Literary Studies](https://mlsanity.com/paper/1808.03137/) (2018)
- [The MuSe 2023 Multimodal Sentiment Analysis Challenge: Mimicked Emotions, Cross-Cultural Humour, and Personalisation](https://mlsanity.com/paper/2305.03369/) (2023)

## Built on by (most cited first, 4 of 4)

- [CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering](https://mlsanity.com/paper/2602.03420/) (2026)
- [Detecting Emotion Drift in Mental Health Text Using Pre-Trained Transformers](https://mlsanity.com/paper/2512.13363/) (2025)
- [Time-Continuous Modeling for Temporal Affective Pattern Recognition in LLMs](https://mlsanity.com/paper/2601.12341/) (2026)
- [Steering Emotional Dynamics for Art Therapy: Controllable Narrative Script Generation through Hierarchically Guided LLM Agents](https://mlsanity.com/paper/2606.16481/) (2026)

## Abstract (arXiv)

Telling stories is an integral part of human communication which can evoke emotions and influence the affective states of the audience. Automatically modeling emotional trajectories in stories has thus attracted considerable scholarly interest. However, as most existing works have been limited to unsupervised dictionary-based approaches, there is no benchmark for this task. We address this gap by introducing continuous valence and arousal labels for an existing dataset of children's stories originally annotated with discrete emotion categories. We collect additional annotations for this data and map the categorical labels to the continuous valence and arousal space. For predicting the thus obtained emotionality signals, we fine-tune a DeBERTa model and improve upon this baseline via a weakly supervised learning approach. The best configuration achieves a Concordance Correlation Coefficient (CCC) of .8221 for valence and .7125 for arousal on the test set, demonstrating the efficacy of our proposed approach. A detailed analysis shows the extent to which the results vary depending on factors such as the author, the individual story, or the section within the story. In addition, we uncover the weaknesses of our approach by investigating examples that prove to be difficult to predict.