[발표] Extended Abstract: Predicting the Morality of a Character Using Character-Centric Embeddings
- 셜이노베이션융합전공
- 조회수339
- 2023-04-29
S. Y. Bae, E. C. Kim and Y. G. Cheong, "Extended Abstract: Predicting the Morality of a Character Using Character-Centric Embeddings," 2023 IEEE International Conference on Big Data and Smart Computing (BigComp), Jeju, Korea, Republic of, 2023, pp. 345-346, doi: 10.1109/BigComp57234.2023.00076.
https://ieeexplore.ieee.org/document/10066592/metrics#metrics
Abstract:
Story generation and analysis have been researched for decades using AI and Natural Language Processing technology. However, while ethics is becoming essential for developing AI applications, little research deals with morality in the narrative. We present the framework to build embeddings for representing characters in terms of the character’s morality. In addition, we propose a morality judgment task using storybooks. We conduct experiments, and the results suggest that word embedding models can learn a character’s morality.