The exponential growth of text documents available on the Internet has created an urgent need for accurate, fast, and general purpose text classification algorithms. However, the "bag of words" representation used for these classification methods is often unsatisfactory as it ignores relationships between important terms that do not co-occur literally. In order to deal with this problem, we integrate background knowledge - in our application: Wikipedia - into the process of classifying text documents. The experimental evaluation on Reuters newsfeeds and several other corpus shows that our classification results with encyclopedia knowledge are much better than the baseline "bag of words " methods.

@inproceedings{PuWang:2007, author = {Wang, Pu and Hu, Jian and Zeng, Hua-Jun and Chen, Lijun and Chen, Zheng}, title = {Improving Text Classification by Using Encyclopedia Knowledge}, booktitle = {Data Mining, 2007. ICDM 2007. Seventh IEEE International Conference on}, year = {2007}, pages = {332-341}, url = {ftp://ftp.computer.org/press/outgoing/proceedings/icdm07/Data/3018a332.pdf}, doi = {10.1109/ICDM.2007.77}, isbn = {978-0-7695-3018-5}, keywords = {classification, text, ol, ****, learning, evaluation, ontology, wikipedia}, abstract = {The exponential growth of text documents available on the Internet has created an urgent need for accurate, fast, and general purpose text classification algorithms. However, the "bag of words" representation used for these classification methods is often unsatisfactory as it ignores relationships between important terms that do not co-occur literally. In order to deal with this problem, we integrate background knowledge - in our application: Wikipedia - into the process of classifying text documents. The experimental evaluation on Reuters newsfeeds and several other corpus shows that our classification results with encyclopedia knowledge are much better than the baseline "bag of words " methods.} }

%0 = inproceedings %A = Wang, Pu and Hu, Jian and Zeng, Hua-Jun and Chen, Lijun and Chen, Zheng %B = Data Mining, 2007. ICDM 2007. Seventh IEEE International Conference on %D = 2007 %T = Improving Text Classification by Using Encyclopedia Knowledge %U = ftp://ftp.computer.org/press/outgoing/proceedings/icdm07/Data/3018a332.pdf