Skip to main content

Making Sense of Research with Rexplore

Enrico Motta ( The Open University, Milton Keynes )

Despite the large number and variety of tools and services available today for exploring scholarly data, current support is still very limited for users who are less interested in searching for publications than in making sense of the dynamics of the research world. Rexplore goes well beyond the current state of the art, by leveraging innovative techniques in large-scale data mining, semantic technologies and visual analytics, to provide a novel solution for exploring and making sense of scholarly data. In particular, Rexplore allows users i) to detect and make sense of key trends in research, e.g., topic shifts within a research community, communities splitting, merging, spawning other communities, etc.; ii) to identify a variety of interesting relations between researchers, which go well beyond the standard ‘static’ relationships, such as co-authorship, which are commonly found in other systems; iii) to perform fine-grained expert search with respect to detailed multi-dimensional parameters; and iv) to analyse research performance at different levels of abstraction, including individual researchers, organizations, countries, and research communities identified on the basis of dynamic criteria. In this talk we will provide an overview of Rexplore, illustrate its many innovative features and discuss in some detail some of its key technical solutions, including the Klink algorithm for automatically constructing fine-grained topic structures and the Research Communities Map Builder (RCMB), which is able to automatically link diachronic topic-based communities over subsequent time intervals to identify significant events in the research world. An empirical task-centric evaluation has shown that Rexplore exhibits a performance that is significantly higher than the other tested systems. In addition, these results are robust both with respect to the background of the users (i.e., expert analysts vs. ‘ordinary’ users) and also with respect to whether the tasks are selected by the evaluators or proposed by the users themselves.

Speaker bio

Prof Enrico Motta has a Ph.D. in Artificial Intelligence from the Open University, where he is currently a Professor in Knowledge Technologies. In the course of his academic career, he has authored about 300 refereed publications and his h-index is 52. His research focuses on large-scale data integration and analysis to support decision making in complex scenarios. In particular, he is currently working on a novel environment for exploring and making sense of scholarly data, which leverages innovative techniques in large-scale data mining, semantic technologies and visual analytics. He is also currently leading the HEFCE-funded MK:Smart project, a £16M flagship initiative which aims to tackle key barriers to economic growth in Milton Keynes through the deployment of innovative data-intensive solutions in the energy, transport and water management sectors. In addition to his main position at the Open University, he is also Editor-in-Chief of the International Journal of Human-Computer Studies, which is ranked as the top journal in HCI by both Microsoft Academic Search and Google. Over the years, he has advised strategic research boards and governments in several countries, including US, UK, The Netherlands, Austria, Finland, and Estonia. He is currently contributing to the Data and Analytics Task Group of the Smart Cities Forum which has been set up by the Office for Science.

Share this: