Noun retrieval effect on text summarization and delivery of personalized news articles to the user’s desktop

Text summarization and categorization, as well as personalization of the results, have always been some of the most demanding information retrieval tasks. Deploying a generalized, multi-functional mechanism that produces good results for the aforementioned tasks seems to be a panacea for most of the text-based, information retrieval needs. In this article, we present the keyword extraction techniques, exploring the effects that part of speech tagging has on the summarization procedure of an existing system. Moreover, we describe the profiling features that are used as an extension to an already constructed news indexing system, PeRSSonal. We are thus enhancing the personalization algorithm that the system utilizes with various features derived from the user’s profile, such as the list of viewed articles and the time spent on them. In addition, we analyze the system’s interconnection channels that are used with the client-side desktop application that was developed and we evaluate the approaches that we propose.