• 한국IT서비스학회지
• /
• 제15권3호
• /
• pp.115-125
• /
• 2016

Novels includes various character names, depending on the genre and the spatio-temporal background of the novels and the nationality of characters. Besides, characters and their names in a novel are created by the author's pen and imagination. As a result, any proper noun dictionary cannot include all kind of character names which have been created or will be created by authors. In addition, since Korean does not have capitalization feature, character names in Korean are harder to detect than those in English. Fortunately, however, Korean has postpositions, such as "-ege" and "hante", used by a sentient being or an animate object (noun). We call such postpositions as animate postpositions in this paper. In a previous study, the authors manually selected character names by referencing both Wikipedia and well-known people dictionaries after utilizing Korean morpheme analyzer, a proper noun dictionary, postpositions (e.g., "-ga", "-eun", "-neun", "-eui", and "-ege"), and titles (e.g., "buin"), in order to extract social networks from three novels translated into or written in Korean. But, the precision, recall, and F-measure rates of character identification are not presented in the study. In this paper, we evaluate the quantitative contribution of animate postpositions to character identification from novels, in terms of precision, recall, and F-measure. The results show that utilizing animate postpositions is a valuable and powerful tool in character identification without a proper noun dictionary from novels translated into or written in Korean.