Using support vector machines to recognize products in e-commerce pages

Common searching engines locate Web pages by means of a lexical comparison among sets of words and the hypertext's contents. These are usually inefficient mechanisms when looking for concepts or objects, such as goods and services, in electronic commerce sites. Semantic Web was announced in 2000 for this purpose, with its implementation initially estimated for ten years. The DEEPSIA project was envisaged to provide a purchaser centered solution to find products for sale on the Web. Testing DEEPSIA on Brazilian sites presented low efficacy, when deciding whether the pages contained or not relevant data. We present here the application and evaluation of Support Vector Machines method to recognize Web pages containing products for sale.