Email updates

Keep up to date with the latest news and content from BMC Bioinformatics and BioMed Central.

Open Access Research article

Contextual weighting for Support Vector Machines in literature mining: an application to gene versus protein name disambiguation

Tapio Pahikkala*, Filip Ginter, Jorma Boberg, Jouni Järvinen and Tapio Salakoski

Author Affiliations

Department of Information Technology, University of Turku and Turku Centre for Computer Science (TUCS), Lemminkäisenkatu 14 A, 20520 Turku, Finland

For all author emails, please log on.

BMC Bioinformatics 2005, 6:157  doi:10.1186/1471-2105-6-157

Published: 22 June 2005

Abstract

Background

The ability to distinguish between genes and proteins is essential for understanding biological text. Support Vector Machines (SVMs) have been proven to be very efficient in general data mining tasks. We explore their capability for the gene versus protein name disambiguation task.

Results

We incorporated into the conventional SVM a weighting scheme based on distances of context words from the word to be disambiguated. This weighting scheme increased the performance of SVMs by five percentage points giving performance better than 85% as measured by the area under ROC curve and outperformed the Weighted Additive Classifier, which also incorporates the weighting, and the Naive Bayes classifier.

Conclusion

We show that the performance of SVMs can be improved by the proposed weighting scheme. Furthermore, our results suggest that in this study the increase of the classification performance due to the weighting is greater than that obtained by selecting the underlying classifier or the kernel part of the SVM.