Personal Research Agents on the Web of Linked Open Data

We introduce the concept of Personal Research Agents as semantics-based entities, capable of helping researchers who have to deal with the overwhelming amount of scientific literature to carry out their daily tasks. We demonstrate how a confluence of state-of-the-art techniques from the Semantic Web and Natural Language Processing domains can realize a proactive agent that can offer personalized services to researchers in retrieval and understanding of scientific literature, based on their background knowledge, interests and tasks. The agent’s knowledge base is populated with knowledge automatically extracted from scientific literature of a given domain using text mining techniques and represented in Linked Open Data (LOD) compliant format. Personalization is achieved through automated user profiling, based on a user’s publications. We implemented these ideas in an open source framework and demonstrate its applicability based on a corpus of open access computer science articles.