텍스트마이닝을 활용한 한⋅중 ‘날씨’ 공기(co-occurrence) 요소 비교 분석

Abstract

Based on the t-scores derived using Text-mining based on Korean and Chinese corpus, this paper analyzes the similarities and differences between the two language phenomena through general nouns, verbs, adjectives, and adverbs in Korean and Chinese. The analysis results are summarized as follows. First, both Korean and Chinese share common ground with elements indicating “external” and “sea” for “Place”. However, while the Korean language is co-occurred with elements that indicate a particular space or range or direction, the Chinese language is co-occurred with elements that indicate a wide range of places or directions. Second, for “Time”, the Korean language is often co-occurred with elements indicating seasons or time zones, but the Chinese language is mainly co-occurred with elements indicating certain times, such as anniversaries, holidays, events and holidays. Third, for “Specification”, both Korean and Chinese have the same co-occurred with specification elements related to rain, wind, snow, temperature, and air, but if you look specifically, the generic word for Korean appears mainly, but there is a difference that hyponym that represent more specific classifications often appear in Chinese. There is also a difference in the Korean language, which often shows the amount of clouds, the amount of sun radiation, and the amount of evaporation, but the Chinese language often shows the amount of air quality. Fourth, for the verbs, the Korean language often has verbs indicating weather conditions, but the Chinese language has differences in the appearance of verbs related to the weather forecast or viewing. There is also a difference in Chinese, which pays attention to the suitability of the weather for certain activities, although Korean pays attention to the dress according to weather conditions. Fifth, for the adjectives, both Korean and Chinese have something in common that they often co-occur with adjectives that indicate weather conditions. Sixth, for the adverbs, there is a difference between the Korean language and the Chinese language, which Korean often co-occurs with “Degree Adverb” but Chinese often co-occurs with “Time Adverb”.