This paper examines how the COVID-19 pandemic associates with Twitch users' emotion, using natural language processing (NLP) as a method. Two comparable sets of text data were collected from Twitch internet relay chats (IRCs): one after the outbreak of the pandemic and another one before that. Positive emotion, negative emotion, and attitude to social interaction were tested by comparing the two text sets via a dictionary-based NLP program. Particularly regarding negative emotion, three negative emotions⸻anger, anxiety, and sadness⸻were measured given the nature of the pandemic. The results show that users' anger and anxiety significantly increased after the outbreak of the pandemic, while changes in sadness and positive emotion were not statistically significant. In terms of attitude to social interaction, users used significantly fewer “social” words after the outbreak of the pandemic than before. These findings were interpreted considering the nature of Twitch as a unique live mixed media platform, and how the COVID-19 pandemic is different from previous crisis events was discussed based on prior literature.