How do language models handle emotional content in video game localization? A computational linguistics approach

This study employs emotion analysis, a natural language processing technique, to examine how language models handle emotional content compared to human translators in video game localization. The analysis is based on a corpus consisting of Chinese subtitles from Black Myth: Wukong, their official English translations, and translations generated by a language model. The findings reveal that, despite similarities between humans and the language model in their translation of emotions, differences exist. Human translators often neutralize emotions through context-dependent strategies, such as omission, addition, and substitution, to address cultural sensitivities and enhance player engagement. In contrast, the language model relies on direct translation to preserve diverse emotions, including negative ones. Such an approach may risk misalignment with the preferences of target audiences due to limited adaptation of tone and cultural nuances. In addition, occasional mistranslation and hallucination were also found. This study highlights the promise of integrating language models into localization workflows and demonstrates the potential of emotion analysis for assessing translation accuracy.