Slang Analysis Based on Variant Information Extraction Focusing on the Time Series Topics

Recently, with the increase in the number of users of Social Networking Sites (SNS), online communications have become more and more common, raising the possibility of using big data on SNS to analyze the diversity of language. Japanese language uses a variety of character types that are combined to create words and phrases. Therefore, it is difficult to morphologically analyze such words and phrases, even though morphological analysis is a basic process in natural language processing. Words and phrases that are not registered in morphological analysis dictionaries are usually not defined strictly, and their semantic interpretation seems to vary depending on the individual. In this study, we chronologically analyze the topics related to slang on Twitter. In this paper, as a validation experiment, we conducted a topic analysis experiment chronologically by using the sequential Tweet data and discussing the difference of topic change according to the slang types.