Designing a Predictive Analytics Solution for Evaluating the Scientific Trends in Information Systems Domain
Journal Title: Webology - Year 2017, Vol 14, Issue 1
Abstract
Full-text articles are mostly provided in electronic formats, but it still remains a challenge to find deeply related works beyond the keywords and abstract contexts. Identification of related scientific articles based on keywords and abstracts help researchers to find desired and informative content, but it requires the utilization of variety of text analytics (mining) methods to address the need. This study investigates information systems (IS) articles to cluster and evaluate the domain of knowledge of recent Information Systems publications using text clustering methods, and then to predict the exact clusters of knowledge of new articles using classification methods. This categorization and predictive learning approach help the scholars and practitioners to find the most relevant articles for their researches and practical endeavors through an automated mechanism. Articles have been collected from the Scopus repository. The dataset has been narrowed to specific areas of recent information systems research. Different text analytics methods such as text normalization, natural language processing (NLP) and clustering algorithms have been applied and the results for each cluster are evaluated by extensive analysis of identified clusters based on their terms frequency and key phrases. Afterwards, different classification algorithms are applied to learn the current clustering and to predict the major subject focus of a newly published article based on the abstract approximation to the previously learned domains of information systems knowledge. The prediction approach helps the scholars identifying the usability of many articles for further research.
Authors and Affiliations
Babak Sohrabi, Iman Raeesi Vanani and Mohsen Baranizade Shineh
Keywords
Related Articles
- EP ID EP687775
- DOI -
- Views 191
- Downloads 0
Bibliometric Analysis and Visualization of the Journal of Artificial Societies and Social Simulation (JASSS) between 2000 and 2018
All scientific journals need to be regularly monitored and evaluated from a bibliometric perspective. The Journal of Artificial Societies and Social Simulation (JASSS) founded in 1998 is dedicated to the topics related t...
Impact Factor, h-index, i10-index and i20-index of Webology
The purpose of this editorial note was to conduct a citation analysis of the Webology journal in order to show the journal impact factor, h-index, i10-index, i20-index, and patent citations. This note indicates to what e...
Editorial Sociology of the Web
Many young scholars at the start of their careers ask, "How can I get published?" An answer to this problem is provided by the Web, which is in fact academia's rich new frontier, providing many excellent opportunities fo...
Identification of the characteristics of e-commerce websites
E-commerce websites must possess certain characteristics in order to attract customers/users. Although previous studies have been conducted to determine some of these characteristics of different categories of websites,...
Deterring digital plagiarism, how effective is the digital detection process?
Academic dishonesty or plagiarism is a growing problem in today's digital world. Use of plagiarism detection tools can assist faculty to combat this form of academic dishonesty. In this article, a special emphasis is giv...