Application of machine learning algorithms in adaptive web-based information systems
Hypertext users often face the difficulty of identifying pages of .information most relevant to their current goals or interests, and are forced to wade through irrelevant pages, even though they know precisely what they are looking for. In order to address this issue, this research has investigated the Technical feasibility and also the utility of applying machine learning algorithms to generate personalised adaptation on the basis of browsing history in hypertext. A Web-based information system called MLTutor has been developed to determine the viability of this approach. The MLTutor has been implemented,tested, and evaluated. The design of MLTutor aims to remove the need for pre-defined user profiles and replace them with a dynamic user profile building scheme in order to provide individual adaptation. This is achieved by a combination o f conceptual clustering and inductive machine learning algorithms. This integration of two machine learning algorithms is a novel approach in the field of machine learning. In the initial prototype of MLTutor, a simple attribute based conceptual clustering algorithm and the ID3 algorithm were implemented. An assessment of the initial prototype highlighted the need for an in-depth investigation into the machine learning component of the prototype. This investigation led to the development of a multiple decision learning algorithm named SG-1 and a scheme for attribute encoding within the system. In order to assess these enhancements a comparative study was conducted with four adaptive variants of MLTutor along with the non-adaptive control. The adaptive variants were developed to allow alternative approaches within the machine learning component of the system to be compared. Two of the variants applied the clustering algorithm dynamically and used two different Cluster selection strategies. These strategies were based on the last page visited and a weighting of recently visited pages. The other adaptive variants used pre-clustered data with the same cluster selection strategies. The comparative evaluation undertaken on the variants used a number of established evaluation criteria and also introduced an original cross analysis scheme to determine how the adaptive component of MLTutor was utilised to complete a set of tasks. This cross analysis scheme highlights a number of weaknesses related to the evaluation methods commonly used in the field of adaptive hypermedia. The results have also highlighted a technical limitation with the particular clustering algorithm employed, specifically the generation of a heterogeneous cluster that results in poor suggestions in some circumstances. The results of the evaluation show that the MLTutor is a functional and robust system. Although the utility of using machine learning algorithms to analyse browsing activity in a hypertext system is unproven, the technical feasibility has been established.