Understanding the meaning of tags » classification

Getting the Most Out of Social Annotations for Web Page Classification

arkaitz — Mon, 27 Jul 2009 08:32:03 +0000

Our paper “Getting the Most Out of Social Annotations for Web Page Classification” has been accepted for publication and presentation at DocEng 2009, the 9th ACM Symposium on Document Engineering to be held in Munich, Germany, from September 15 to 18, 2009.

Abstract

User-generated annotations on social bookmarking sites can provide interesting and promising metadata for web document management tasks like web page classification. These user-generated annotations include diverse types of information, such as tags and comments. Nonetheless, each kind of annotation has a different nature and popularity level. In this work, we analyze and evaluate the usefulness of each of these social annotations to classify web pages over a taxonomy like that proposed by the Open Directory Project. We compare them separately to the content-based classification, and also combine the different types of data to augment performance. Our experiments show encouraging results with the use of social annotations for this purpose, and we found that combining these metadata with web page content improves even more the classifier’s performance.

Share/Save

Clasificación de Páginas Web con Anotaciones Sociales

arkaitz — Fri, 19 Jun 2009 09:58:37 +0000

Our paper “Clasificación de Páginas Web con Anotaciones Sociales” has been accepted for publication and presentation at SEPLN 2009, XXV edición del Congreso Anual de la Sociedad Española para el Procesamiento del Lenguaje Natural to be held in Donostia-San Sebastián, from September 8 to 10, 2009.

Abstract

Las anotaciones generadas por usuarios en sistemas de marcadores sociales pueden proveer metadatos interesantes y muy útiles para la clasificación de páginas web. Estas anotaciones incluyen diversos tipos de información, como etiquetas y comentarios. No obstante, cada tipo de anotación tiene una naturaleza y un nivel de popularidad diferente. En este trabajo, analizamos y evaluamos la utilidad de cada una de estas anotaciones sociales para clasificar páginas web sobre una taxonomía como la del Open Directory Project. Las comparamos por separado a la clasificación basada en contenido, y también las combinamos. Nuestros experimentos muestran resultados prometedores con la utilización de anotaciones sociales para este propósito. Y además indican que su combinación con el contenido textual mejora el rendimiento de la clasificación.

Share/Save

Is Unlabeled Data Suitable for Multiclass SVM-based Web Page Classification?

arkaitz — Fri, 17 Apr 2009 08:52:24 +0000

Our paper “Is Unlabeled Data Suitable for Multiclass SVM-based Web Page Classification?“ has been accepted for publication and presentation at the NAACL HLT 2009 Workshop on Semi-supervised Learning for Natural Language Processing to be held in Boulder, Colorado, from May 31 to June 5, 2009.

Abstract

Support Vector Machines present an interesting and effective approach to solve automated classification tasks. Although it only handles binary and supervised problems by nature, it has been transformed into multiclass and semi-supervised approaches in several works. A previous study on supervised and semi-supervised SVM classification over binary taxonomies showed how the latter clearly outperforms the former, proving the suitability of unlabeled data for the learning phase in this kind of tasks. However, the suitability of unlabeled data for multiclass tasks using SVM has never been tested before. In this work, we present a study on whether unlabeled data could improve results for multiclass web page classification tasks using Support Vector Machines. As a conclusion, we encourage to rely only on labeled data, both for improving (or at least equaling) performance and for reducing the computational cost.

Share/Save