@inproceedings{ff50ed9da667413ea25c78c798a0760d,
title = "Bringing bag-of-phrases to ODP-based text classification",
abstract = "The Open Directory Project (ODP) is a large scale, high quality and publicly available web directory. Many studies and real-world applications build on an ODP-based classifier. However, existing approaches use traditional bag-of-words representation of text to develop an ODP-based classifier and words alone do not always provide atomic units of semantic meaning. In this paper, we propose a novel framework to better understand the semantic meaning of text by bringing bag-of-phrases to ODP-based text classification. The proposed method employs a syntactic tree to extract phrases from ODP and applies a phrase selection method to alleviate the high dimensionality problem of bag-of-phrases. The conducted evaluation results demonstrate that our approach outperforms the state-of-the-art methods in classification performance.",
keywords = "open directory project, syntactic structure, text classification, text mining",
author = "Haeyong Shin and Ryu, {Byung Gul} and Ryu, {Woo Jong} and Geunjae Lee and Sang-Geun Lee",
note = "Funding Information: This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT and future Planning (2015R1A2A1A10052665). Publisher Copyright: {\textcopyright} 2016 IEEE.; International Conference on Big Data and Smart Computing, BigComp 2016 ; Conference date: 18-01-2016 Through 20-01-2016",
year = "2016",
month = mar,
day = "3",
doi = "10.1109/BIGCOMP.2016.7425975",
language = "English",
series = "2016 International Conference on Big Data and Smart Computing, BigComp 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "485--488",
booktitle = "2016 International Conference on Big Data and Smart Computing, BigComp 2016",
}