Genre-based decomposition of email class noise

Authors:
Aleksander Kolcz;Gordon V. Cormack
Affiliations:
Microsoft, Redmond, USA;University of Waterloo, Waterloo, Canada
Venue:
Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining
Year:
2009

Citing 9
Cited 0

Probabilistic combination of text classifiers using reliability indicators: models and results

SIGIR '02 Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval
Improving Classification by Removing or Relabeling Mislabeled Instances

ISMIS '02 Proceedings of the 13th International Symposium on Foundations of Intelligent Systems
Adversarial classification

Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
Online supervised spam filter evaluation

ACM Transactions on Information Systems (TOIS)
Spam Filtering Using Statistical Data Compression Models

The Journal of Machine Learning Research
Relaxed online SVMs for spam filtering

SIGIR '07 Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval
Email Spam Filtering: A Systematic Review

Foundations and Trends in Information Retrieval
The use of the area under the ROC curve in the evaluation of machine learning algorithms

Pattern Recognition
Ensemble methods for noise elimination in classification problems

MCS'03 Proceedings of the 4th international conference on Multiple classifier systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Corruption of data by class-label noise is an important practical concern impacting many classification problems. Studies of data cleaning techniques often assume a uniform label noise model, however, which is seldom realized in practice. Relatively little is understood, as to how the natural label noise distribution can be measured or simulated. Using email spam-filtering data, we demonstrate that class noise can have substantial content specific bias. We also demonstrate that noise detection techniques based on classifier confidence tend to identify instances that human assessors are likely to label in error. We show that genre modeling can be very informative in identifying potential areas of mislabeling. Moreover, we are able to show that genre decomposition can also be used to substantially improve spam filtering accuracy, with our results outperforming the best published figures for the trec05-p1 and ceas-2008 benchmark collections.