Other formats:
BibTeX
LaTeX
RIS
@article{719182,
author = {Pomikálek, Jan and Řehůřek, Radim},
article_number = {1},
keywords = {machine learning; text categorization; preprocessing; feature selection},
language = {eng},
issn = {1307-4318},
journal = {International Journal of Applied Science, Engineering and Technology},
title = {The Influence of Preprocessing Parameters on Text Categorization},
url = {http://www.waset.org/pwaset/v19/v19-82.pdf},
volume = {4/2007},
year = {2007}
}
TY - JOUR
ID - 719182
AU - Pomikálek, Jan - Řehůřek, Radim
PY - 2007
TI - The Influence of Preprocessing Parameters on Text Categorization
JF - International Journal of Applied Science, Engineering and Technology
VL - 4/2007
IS - 1
SP - 430-434
EP - 430-434
SN - 13074318
KW - machine learning
KW - text categorization
KW - preprocessing
KW - feature selection
UR - http://www.waset.org/pwaset/v19/v19-82.pdf
N2 - Results of a large scale study on mutual influence of preprocessing parameters in automated text categorization are presented and analyzed. These parameters include choice of tokenizer, feature selection, stemming, term weighing and data amount in combination with various Machine Learning algorithms.
ER -
POMIKÁLEK, Jan and Radim ŘEHŮŘEK. The Influence of Preprocessing Parameters on Text Categorization. \textit{International Journal of Applied Science, Engineering and Technology}. 4/2007, No~1, p.~430-434. ISSN~1307-4318. 2007.
|
