@inproceedings{Shen:2004:WCT:1008992.1009035,
  abstract = {Web-page classification is much more difficult than pure-text classification due to a large variety of noisy information embedded in Web pages. In this paper, we propose a new Web-page classification algorithm based on Web summarization for improving the accuracy. We first give empirical evidence that ideal Web-page summaries generated by human editors can indeed improve the performance of Web-page classification algorithms. We then propose a new Web summarization-based classification algorithm and evaluate it along with several other state-of-the-art text summarization algorithms on the LookSmart Web directory. Experimental results show that our proposed summarization-based classification algorithm achieves an approximately 8.8% improvement as compared to pure-text-based classification algorithm. We further introduce an ensemble classifier using the improved summarization algorithm and show that it achieves about 12.9% improvement over pure-text based methods.},
  acmid = {1009035},
  address = {New York, NY, USA},
  author = {Shen, Dou and Chen, Zheng and Yang, Qiang and Zeng, Hua-Jun and Zhang, Benyu and Lu, Yuchang and Ma, Wei-Ying},
  booktitle = {Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval},
  doi = {10.1145/1008992.1009035},
  interhash = {328ff5b51cb573cd1d253f339892c029},
  intrahash = {b83fca9d43e5afdea78b9791cc07890c},
  isbn = {1-58113-881-4},
  location = {Sheffield, United Kingdom},
  numpages = {8},
  pages = {242--249},
  publisher = {ACM},
  series = {SIGIR '04},
  title = {Web-page classification through summarization},
  url = {http://doi.acm.org/10.1145/1008992.1009035},
  year = 2004
}