Affiliation:
1. Knowledge Engineering Laboratory, Department of Computer Engineering, Chung-Ang University, Seoul, Korea
Abstract
Abstract
Recently, with an increasing number of metaphor studies being conducted, research on metaphor interpretation has set off an upsurge. Although a multitude of studies on the interpretation of metaphors exists, many are limited to the understanding of literal meanings without attempting an interpretation of hidden emotions in metaphorical expressions. There are particularly few studies on metaphorical emotions interpretation in literary studies with rich and implicit emotions, such as classical Chinese poetry. This study proposes the interpretation of the metaphorical emotions of special objects in Chinese poetry based on emotion distribution. We present a statistical approach to calculate the emotion distribution of our target objects by exploiting contextual emotion mining. According to the emotion distribution, the emotion with the highest probability is considered the metaphorical emotion of the target object. Subsequently, the metaphorical emotion can be determined as a positive or negative sentiment based on expert annotations. Using the proposed method, we have tested two representative objects, ‘月’ (moon) and ‘风’ (wind), and the accuracy performances were 84% and 83.33%, respectively, for sentiment detection and 66% and 70% for emotion-specific metaphorical interpretation. The results demonstrate that our approach can be used to assist readers with metaphorical emotional understanding in Chinese poetry.
Publisher
Oxford University Press (OUP)
Subject
Computer Science Applications,Linguistics and Language,Language and Linguistics,Information Systems
Reference26 articles.
1. Metaphor interpretation using paraphrases extracted from the web;Bollegala;PloS One,2013
2. The emotions of everyday existence mirrored in Chinese popular poetry of the mid-seventeenth to the mid-nineteenth century;Elvin;Self as Image in Asian Theory and Practice. New York, USA: Springer,1998
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献