Intelligent Information Systems for Web Product Search

Over the last few years, we have experienced an increase in online shopping. Consequently, there is a need for efficient and effective product search engines. The rapid growth of e-commerce, however, has also introduced some challenges. Studies show that users can get overwhelmed by the information and offerings presented online while searching for products. In an attempt to lighten this information overload burden on consumers, there are several product search engines that aggregate product descriptions and price information from the Web and allow the user to easily query this information. Most of these search engines expect to receive the data from the participating Web shops in a specific format, which means Web shops need to transform their data more than once, as each product search engine requires a different format. Because currently most product information aggregation services rely on Web shops to send them their data, there is a big opportunity for solutions that aim to tackle this problem using a more automated approach. This dissertation addresses key aspects of implementing such a system, including hierarchical product classification, entity resolution, ontology population and schema mapping, and lastly, the optimization of faceted user interfaces. The findings of this work show us how one can design Web product search engines that automatically aggregate product information while allowing users to perform effective and efficient queries.