Cognitive Approaches for the Semantic Web (Dagstuhl Seminar 12221)

Abstract

A major focus in the design of Semantic Web ontology languages used to be on finding a suitable balance between the expressivity of the language and the tractability of reasoning services defined over this language. This focus mirrors the original vision of a Web composed of machine readable and understandable data. Similarly to the classical Web a few years ago, the attention is recently shifting towards a user-centric vision of the Semantic Web. Essentially, the information stored on the Web is from and for humans. This new focus is not only reflected in the fast growing Linked Data Web but also in the increasing influence of research from cognitive science, human computer interaction, and machine-learning. Cognitive aspects emerge as an essential ingredient for future work on knowledge acquisition, representation, reasoning, and interactions on the Semantic Web. Visual interfaces have to support semantic-based retrieval and at the same time hide the complexity of the underlying reasoning machinery from the user. Analogical and similarity-based reasoning should assist users in browsing and navigating through the rapidly increasing amount of information. Instead of pre-defined conceptualizations of the world, the selection and conceptualization of relevant information has to be tailored to the user's context on-the-fly. This involves work on ontology modularization and context-awareness, but also approaches from ecological psychology such as affordance theory which also plays an increasing role in robotics and AI. During the Dagstuhl Seminar 12221 we discussed the most promising ways to move forward on the vision of bringing findings from cognitive science to the Semantic Web, and to create synergies between the different areas of research. While the seminar focused on the use of cognitive engineering for a user-centric Semantic Web, it also discussed the reverse direction, i.e., how can the Semantic Web work on knowledge representation and reasoning feed back to the cognitive science community.