Rexplore System
An Rexplore System is a Scholarly Corpus Analysis System.
- Context:
- It can have an advanced graphical interface.
- It can help explore Scholarly Authors, Scholarly Topics, and Research Communities.
- See: Scholarly Corpus Analysis, Klink-2, TechMiner System, Knowledge Base System, Topic Trend Analysis, Klink-2 Computer Science Ontology (CSO).
References
2016
- http://technologies.kmi.open.ac.uk/rexplore/
- QUOTE: Rexplore leverages novel solutions in large-scale data mining, semantic technologies and visual analytics, to provide an innovative environment for exploring and making sense of scholarly data.
In particular, Rexplore allows users:- To detect and make sense of important trends in research, such as, significant migrations of researchers from one area to another, the emergence of new topics, the evolution of communities within a particular area, and several others.
- To identify a variety of interesting relations between researchers, e.g., recognizing authors who share similar research trajectories. These relations go well beyond the standard co-authorship links or relationships informed by social networks, which are commonly found in other systems.
- To perform fine-grained expert search with respect to detailed multi-dimensional parameters.
- To analyse research performance at different levels of abstraction, including individual researchers, organizations, countries, and research communities identified on the basis of dynamic criteria.
- To automatically classify book collections, authors, conferences and other research entities according to the associated research topics.
- An important aspect of Rexplore is that it does not rely on manually-generated taxonomies of research areas, which tend to be shallow and date very rapidly, but uses instead an innovative ontology population algorithm, Klink-2, which automatically constructs a semantic network of fine-grained research areas, linked by semantic relations, such as sameAs and subAreaOf. The use of Klink-2 ensures a fine-grained handling of research areas and affords Rexplore a very high level of precision and recall in associating topics to publications and researchers.
Rexplore integrates scholarly data from major commercial publishers, as well as other resources, such as DBpedia and GeoNames. As of January 2016, Rexplore includes metadata on 16 million papers and 11 million authors. It relies on an ontology of Computer Science topics, automatically generated by means of the Klink-2 algorithm, which contains about 15K research topics linked by about 70K semantic relationships.
Rexplore offers an advanced graphical interface, comprising a variety of innovative and fine grained visualizations, which support users in exploring authors, topics, and research communities. To support effective exploration, all graphical elements can be clicked on, thus enabling a seamless and contextualized navigation. In the above gallery we show a few snapshots of the system in action. More details can be found in the associated publications.
- QUOTE: Rexplore leverages novel solutions in large-scale data mining, semantic technologies and visual analytics, to provide an innovative environment for exploring and making sense of scholarly data.
- (Osborne et al., 2016) ⇒ Francesco Osborne, Helene de Ribaupierre, and Enrico Motta. (2016). “TechMiner: Extracting Technologies from Academic Publications.” In: Proceedings of 20th International Conference on Knowledge Engineering and Knowledge Management (EKAW 2016).
- QUOTE: The Klink-2 Computer Science Ontology (CSO) is a very large ontology of Computer Science that was created by running the Klink-2 algorithm [16] on about 16 million publications in the field of Computer Science extracted from the Scopus repository. The Klink-2 algorithm combines semantic technologies, machine learning and external sources to generate a fully populated ontology of research areas. It was built to support the Rexplore system (Osborne et al, 2013) and to enhance semantically a number of analytics and data mining algorithms. The current version of the CSO ontology includes 17,000 concepts and about 70,000 semantic relationships.
2014
- (Osborne & Motta, 2014) ⇒ Francesco Osborne, and Enrico Motta. (2014). “Rexplore: Unveiling the Dynamics of Scholarly Data.” In: Digital Libraries (JCDL), 2014 IEEE / ACM Joint Conference on, pp. 415-416 . IEEE,
2013
- (Osborne et al., 2013) ⇒ Francesco Osborne, Enrico Motta, and Paul Mulholland. (2013). “Exploring Scholarly Data with Rexplore.” In: Proceedings of the 12th International Semantic Web Conference - Part I. ISBN:978-3-642-41334-6 doi:10.1007/978-3-642-41335-3_29