Title: An effective topic-based ranking technique for categorised research articles

Authors: Rajendra Kumar Roul; Jajati Keshari Sahoo

Addresses: Department of Computer Science, Birla Institute of Technology and Science Pilani, K K Birla Goa Campus, Zuarinagar, Goa-403726, India ' Department of Mathematics, Birla Institute of Technology and Science Pilani, K K Birla Goa Campus, Zuarinagar, Goa-403726, India

Abstract: The number of research articles is increasing very rapidly on the web due to the large volume of research work happening everyday. Maintaining and searching the required articles according to the user requirements is the need of the hour. Classification and ranking are the two important techniques of information retrieval which can shed light in this direction. This paper proposes an effective ranking approach which is the follow-up of our earlier classification work in which by using the keywords extracted from the keyword section of the articles, a huge volume of articles are classified into their respective categories. To rank these articles in each category, the proposed ranking approach uses latent Dirichlet allocation which transforms the text into the topics and then applies inverted indexing technique on it. Five benchmark datasets are used for experimental work. Results obtained from the experiment indicate that the performance of the proposed ranking technique is promising.

Keywords: hierarchical classification; inverted indexing; latent Dirichlet allocation; LDA; ranking; text categorisation.

DOI: 10.1504/IJCSYSE.2018.090642

International Journal of Computational Systems Engineering, 2018 Vol.4 No.1, pp.35 - 45

Received: 09 Feb 2017
Accepted: 19 Jul 2017
Published online: 25 Mar 2018 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article