Exploiting Multidimensional Data for web Site Automation

• Main Author: Domingues, Marcos Aurélio
• Format: Dissertation
• Language: English
• Published: ProQuest Dissertations & Theses 01-01-2024
• Subjects: Computer science; Data mining; Data warehouses; Educational technology; Information science; Online instruction; Recommender systems
• ISBN: 9798384182849

Besides the user (the human agent who browses through the web site) there are generally two other important roles in the context of a web site, the owner and the editor. The owner is the person or organization that defines the goals for the site and manages the editor’s activity. The editor is the person in charge of creating, updating and deleting contents. He/she monitors and evaluates at any time the site activity, managing the site in accordance with both the goals of the owner and of the user.Due to the constant demand for new information and timely updates of services and content in order to satisfy the user’s needs, web site automation has emerged as a solution to automate several personalization and management activities of a web site. One of the goals of automation is the reduction of the editor’s effort, and consequently of the costs for the owner. The other goal is that the site can more timely adapt to the behavior of the user, improving the browsing experience and helping the user in achieving his/her own goals. The automation of a web site involves different technologies to gather, analyze and provide access to data. Among the various technologies, data warehousing, web mining and recommender systems can enable organizations to improve their web sites/businesses. In this thesis, we exploit the use of multidimensional data (i.e., data involving several dimensions or aspects) for web site automation.In the first part of our work, we propose a data warehouse that is developed to be a repository of information to support different web site automation and monitoring activities. We implemented our data warehouse and used it as a repository of information in three different case studies related to the areas of e-commerce, e-learning and e-news. The case studies showed that our data warehouse is appropriated for web site automation in different contexts. In all cases, the use of the data warehouse was quite simple and with a good response time, mainly because of the simplicity of its structure.In the second part, we propose a multidimensional approach, called DaVI (Dimensions as Virtual Items), that enables the application of common two-dimensional top-N recommender algorithms for the generation of recommendations using additional dimensions (e.g., contextual or background information). We use the proposed data warehouse to provide web data to the multidimensional approach. The main advantage of the DaVI approach is that it can be applied on several existing twodimensional recommendation algorithms. In order to evaluate its effectiveness, we implemented the DaVI approach on two different top-N recommender algorithms, Item-based Collaborative Filtering and Association Rules based, and ran an extensive set of experiments in three different real world data sets. The empirical results demonstrated that the DaVI approach enables the application of existing two-dimensional recommendation algorithms in multidimensional data, exploiting the useful information of these data to enhance top-Nrecommender systems.