@inproceedings{7f8adb64775c45f4b3f3fcde9f517d77,
title = "Analysis of preprocessing methods on classification of Turkish texts",
abstract = "Preprocessing is an important task and critical step in information retrieval and text mining. The objective of this study is to analyze the effect of preprocessing methods in text classification on Turkish texts. We compiled two large datasets from Turkish newspapers using a crawler. On these compiled data sets and using two additional datasets, we perform a detailed analysis of preprocessing methods such as stemming, stopword filtering and word weighting for Turkish text classification on several different Turkish datasets. We report the results of extensive experiments.",
keywords = "Data preprocessing, Text Classification, Turkish Text Classification, stemming, stopword removal",
author = "Dilara Torunoǧlu and Erhan {\c C}akirman and Ganiz, \{Murat Can\} and Selim Akyoku{\c s} and G{\"u}rb{\"u}z, \{M. Zahid\}",
year = "2011",
doi = "10.1109/INISTA.2011.5946084",
language = "English",
isbn = "9781612849195",
series = "INISTA 2011 - 2011 International Symposium on INnovations in Intelligent SysTems and Applications",
pages = "112--117",
booktitle = "INISTA 2011 - 2011 International Symposium on INnovations in Intelligent SysTems and Applications",
note = "2011 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2011 ; Conference date: 15-06-2011 Through 18-06-2011",
}