AAAI Publications, Ninth Artificial Intelligence and Interactive Digital Entertainment Conference

Font Size: 
Identifying Personal Narratives in Chinese Weblog Posts
Andrew S. Gordon, Luwen Huangfu, Kenji Sagae, Wenji Mao, Wen Chen

Last modified: 2013-11-13


Automated text classification technologies have enabled researchers to amass enormous collections of personal narratives posted to English-language weblogs. In this paper, we explore analogous approaches to identify personal narratives in Chinese weblog posts as a precursor to the future empirical studies of cross-cultural differences in narrative structure. We describe the collection of over half a million posts from a popular Chinese weblog hosting service, and the manual annotation of story and nonstory content in sampled posts. Using supervised machine learning methods, we developed an automated text classifier for personal narratives in Chinese posts, achieving classification accuracy comparable to previous work in English. Using this classifier, we automatically identify over sixty-four thousand personal narratives for use in future cross-cultural analyses and Chinese-language applications of narrative corpora.


Narrative; Natural language processing; Weblogs

Full Text: PDF