This paper aims to test deep-learning-based Korean language models’ capacity to learn and detect social registers embedded in speech data, specifically age, gender, and regional dialects. A comprehensive understanding of linguistic phenomena requires contextualizing speech based on speakers’ age, gender, and geographic background, along with the processing of syntactic structures. To bridge the gap between human language understanding and model processing, we fine-tuned three representative Korean language models—KR-BERT, KoELECTRA-base, and KLUE-RoBERTa-base—using transcribed data from 4,000 hours of speech by middle-aged and elderly Korean speakers. The findings reveal that KoELECTRA-base outperformed the other two models across all social registers, which is likely attributed to its larger vocabulary and parameters size. Among the dialects, the Jeju dialect showed the highest accuracy in inference, which is attributed to its distinctiveness, making it easier for the models to detect. In addition to the fine-tuning process, we have made our fine-tuned models publicly available to support researchers interested in Korean computational sociolinguistics.

Despite the massive impact of COVID-19 on society, beyond the numbers of confirmed cases and deaths, there remains a lack of large-scale data depicting the effects of the virus on the society of the Republic of Korea. To fill this gap, we collected 1.822 million news articles with more than 1 billion morphemes from January 2020 to June 2022, creating a Korean version of the Coronavirus Corpus. This corpus is introduced in the current study. In addition, to demonstrate how such massive corpus can be utilized, we conducted information theoretical analyses to see how the stance of the press media on topics such as vaccines and social distancing affected the COVID-19 situation in the Republic of Korea. Specifically, we utilized several computational linguistic skills including concordance building and sentiment analysis through both traditional and machine learning techniques and measured the transfer entropy to estimate the impact with information theory. The results suggest that the overall impact of the press media on the society was minimal to non-existent.