doi: 10.4304/jsw.9.10.2564-2573
A Two-Stage Method for Scientific Papers Analysis
- 1 College of Information Science and Engineering, Hunan University, Changsha, China
- 2 College of Science and Technology, University of Rwanda, Kigali, Rwanda
Abstract
A considerable amount of research is beingconducted by many people (researchers, graduate students,professors etc) everyday. Finding information about aspecific topic is one of the most time consuming activities ofthose people. People doing research have to search, read andanalyze multiple research papers, e-books and otherdocuments and then determine what they contain anddiscover knowledge from them. Many available resourcesare in the form of unstructured text format of long textpages which require long time to read and analyze. In thispaper we propose a two-stage method for scientific paperanalysis. The method uses information extraction to extractthe main idea key sentences (mainly needed by the mostreaders) from the paper and the extracted paper’sinformation is then organized in a structured format andgrouped in different clusters according to their topics usinga multi-word based clustering method. The proposedmethod combines different features in paper’s topicsextraction and uses multi-word matching feature inselection of initial centroids for clustering. The proposedmethod can help readers to access and analyze multipleresearch papers documents timely and efficiently.Conducted experiments show the effectiveness andusefulness of our proposed approach.
Keywords
- text mining
- information extraction
- tex
How to Cite
Damien Hanyurwimfura and Bo Liao, "A Two-Stage Method for Scientific Papers Analysis," Journal of Software, vol. 9, no. 10, pp. 2564-2573, 2014. https://doi.org/ 10.4304/jsw.9.10.2564-2573
Copyright & License
Copyright © 2014 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).