Poetic Features for Poem Recognition: A Comparative Study
The Journal of Pattern Recognition Research (JPRR) provides an international forum for the electronic publication of high-quality research and industrial experience articles in all areas of pattern recognition, machine learning, and artificial intelligence. JPRR is committed to rigorous yet rapid reviewing. Final versions are published electronically
(ISSN 1558-884X) immediately upon acceptance.
Poetic Features for Poem Recognition: A Comparative Study
Hamid R. Tizhoosh, Farhang Sahba, Rozita Dara
JPRR Vol 3, No 1 (2008); doi:10.13176/11.62 
Download
Hamid R. Tizhoosh, Farhang Sahba, Rozita Dara
Abstract
Poetry is a form of art that is used to express emotions and feelings. Humans can easily distinguish poetry without any sophisticated tools. This study is concerned with developing intelligent methods which can be used to distinguish poem from prose. The goal is to distinguish and extract effective poetic features with which poems/lyrics can be accurately classified from other type of texts. In this paper, we propose five different approaches to poem classification. In each approach, we extracted a different set of poetic features and evaluated their performances against each other. In addition, we empirically assessed the effectiveness of traditional text classification methods for poem recognition and compared it with the proposed poetic feature. While all of these approaches performed well, some showed superior results. Findings of this study suggest that the proposed features generate classifiers with accuracy as high as 97.3% on 850 text documents collected for this study, which can be used for poem mining in large databases and classifying the Internet content.
JPRR Vol 3, No 1 (2008); doi:10.13176/11.62 | Full Text  | Share this paper: