||Author(s): I. Katakis, G. Tsoumakas, I. Vlahavas.
Title: “Dynamic Feature Space and Incremental Feature Selection for the Classification of Textual Data Streams”.
Click here to download the PDF (Acrobat Reader) file (10 pages).
Text Classification, Data Streams, Concept Drift, Dynamic Feature Space, Incremental Feature Selection.
ECML/PKDD-2006 International Workshop on Knowledge Discovery from Data Streams, pp. 107-116, Berlin, Germany, 2006.
Abstract: Real world text classification applications are of special interest for the machine learning and data mining community, mainly because they introduce and combine a number of special difficulties. They deal with high dimensional, streaming, unstructured, and, in many occasions, concept drifting data. Another important peculiarity of streaming text, not adequately discussed in the relative literature, is the fact that the feature space is initially unavailable. In this paper, we discuss this aspect of textual data streams. We underline the necessity for a dynamic feature space and the utility of incremental feature selection in streaming text classification tasks. In addition, we describe a computationally undemanding incremental learning framework that could serve as a baseline in the field. Finally, we introduce a new concept drifting dataset which could assist other researchers in the evaluation of new methodologies.
Concept drifting datasets descibed in paper