Tang Y.-J.Li C.-Y.Chen H.-H.2019-07-102019-07-1020119781577355212https://scholars.lib.ntu.edu.tw/handle/123456789/413154While microblogging has gained popularity on the Internet, analyzing and processing short messages has become a challenging task in natural language processing. This paper analyzes the differences between Internet short messages (or "microtext") and general articles by comparing the Plurk Corpus and the Sinica Balanced Corpus. Likelihood ratio and the t?ngy? c?c?l?n thesaurus are adopted to analyze the lexical semantics of frequent terms in each corpus. Furthermore, the NTUSD sentiment dictionary is used to compare the sentiment distribution of the two corpora. The result is also applied to sentiment transition analysis.conference paper2-s2.0-80054930795https://www.scopus.com/inward/record.uri?eid=2-s2.0-80054930795&partnerID=40&md5=0fbc6d088760a38a224a42d53ef5e128