This paper introduces CharMoral, a dataset designed to analyze the moral evolution of characters in long-form narratives. CharMoral, built from 1,337 movie synopses, includes annotations for character actions, context, and morality labels. To automatically construct CharMoral, we propose a four-stage framework, utilizing Large Language Models, to automatically classify actions as moral or immoral based on context. Human evaluations and various experiments confirm the framework’s effectiveness in moral reasoning tasks in multiple genres. Our code and the CharMoral dataset are publicly available at https://github.com/BaeSuyoung/CharMoral.

Emotion significantly influences human behavior and decision-making processes. We propose a labeling methodology grounded in Plutchik’s Wheel of Emotions theory for emotion classification. Furthermore, we employ a Mixture of Experts (MoE) architecture to evaluate the efficacy of this labeling approach, by identifying the specific emotions that each expert learns to classify. Experimental results reveal that our methodology improves the performance of emotion classification.

In this paper, we describe our work for the CreativeSumm 2022 Shared Task, Automatic Summarization for Creative Writing. The task is to summarize movie scripts, which is challenging due to their long length and complex format. To tackle this problem, we present a two-stage summarization approach using both the abstractive and an extractive summarization methods. In addition, we preprocess the script to enhance summarization performance. The results of our experiment demonstrate that the presented approach outperforms baseline models in terms of standard summarization evaluation metrics.

As the size of investment for movie production grows bigger, the need for predicting a movie’s success in early stages has increased. To address this need, various approaches have been proposed, mostly relying on movie reviews, trailer movie clips, and SNS postings. However, all of these are available only after a movie is produced and released. To enable a more earlier prediction of a movie’s performance, we propose a deep-learning based approach to predict the success of a movie using only its plot summary text. This paper reports the results evaluating the efficacy of the proposed method and concludes with discussions and future work.