MLICC: A Multi-Label and Incremental Centroid-Based Classification of Web Pages by Genre
This paper proposes an improved centroid-based approach to classify web pages by genre using character n-grams extracted from URL, title, headings and anchors. To deal with the complexity of web pages and the rapid evolution of web genres, our approach implements a multi-label and incremental scheme in which web pages are classified one by one and can be affected to more than one genre. According to the similarity between the new page and each genre centroid, our approach either adjust the genre centroid or considers the new page as noise page and discards it. Conducted experiments show that our approach is very fast and achieves superior results over existing multi-label classifiers.
KeywordsMulti-label Incremental Centroid genre classification character n-grams
Unable to display preview. Download preview PDF.
- Read, J., Pfahringer, B., Holmes, G.: Multi-label Classification Using Ensembles of Pruned Sets. In: 8th IEEE International Conference on Data Mining (2008)Google Scholar
- Salton, G.: Automatic Text Processing: The Transformation Analysis and Retrieval of Information by Computer. Addison-Wesley (1989)Google Scholar
- Santini, M.: Automatic Identification of Genr. Web Pages. PhD thesis, University of Brighton, UK (2007)Google Scholar
- Shepherd, M., Watters, C.: Evolution of Cybergenre. In: 31 Hawaiian International Conference on System Sceinces (1998)Google Scholar
- Vedrana, V., Mitja, L., Matjaž, G.: Multi-Label Approaches to Web Genre Identification. Journal of Language and Computational Linguistics 24(1), 97–114 (2009)Google Scholar
- Vidulin, V., Luštrek, M., Gams, M.: Using Genres to Improve Search Engines. In: 1st International Workshop: Towards Genre-Enabled Search Engines: The Impact of Natural Language Processing, Borovest, Bulgaria, pp. 45–51 (2007)Google Scholar
- Zhang, M., Zhou, Z.: A K-Nearest Neighbor based Algorithm for Multi-label Classification. In: 1st IEEE International Conference on GrC, China (2005)Google Scholar