Improving Access to Information through Conceptual Classification

Abstract

Overwhelming the users with large amount of information on the Web has resulted in users' inability to find the information and their dissatisfaction with available information searching and filtering systems. On the other hand, the information is distributed over many websites and a large part of it (for example news) is updated frequently. Keeping track of the changes in huge amount of information is a real problem for users. Due to the great impact the information has on people's lives and business decision-making, much research has been done on the efficient ways of accessing and analyzing the information. This thesis will propose a conceptual classification method and ranking of the information in order to provide better user access to a wider range of information, it also provides the information that may help in analyzing the global trends in various fields. In order to demonstrate the effectiveness of this method, a feed aggregator system has been developed and evaluated through this thesis. To improve the flexibility and adaptability of the system, we have adopted the agent-oriented software engineering architecture that has also helped facilitating the development process. In addition, since the system deals with storing and processing large amounts of information, that requires a large number of resources the cloud platform service has been used as a platform for deploying the application. The result was a cloud based software service that benefited from the unlimited on-demand resources. To take advantage of the available features of public cloud computing platforms, those supporting the agent-oriented design, the multi-agent system was implemented by mapping the agents to the cloud computing services. In addition, the cloud queue service that is provided by some cloud providers such as Microsoft and Amazon was used to implement indirect communication among the agents in the multi-agent system.