Analysis of Text Mining from Full-text Articles and Abstracts by Postgraduates Students in Selected Nigeria Universities

Mariam Taiwo Ibrahim, Adeyinka Tella


Purpose: This study analysed text mining from full-text articles and abstracts by postgraduate students in selected Nigeria universities.

Design/methodology/approach: The study adopted a survey research design using a questionnaire as the instrument for data collection from 357 postgraduate students drawn using Raosoft sample size calculator. Six research questions were developed and answered.

Finding: The findings demonstrate that postgraduate students mined texts from full texts articles mostly to write a dissertation, for personal academic development and to prepare research seminars. It also revealed that postgraduate students mined texts from abstracts majorly to write dissertations and prepare for research seminars; postgraduate students mined texts using information extraction technique, information retrieval technique, and summarization. The texts are mined mostly form PDF format, followed by Microsoft word format and HTML format (Web pages). Postgraduate students prefer mining texts from full-text articles than from abstracts and the sources postgraduate students mostly mine text is through the World Wide Web, followed by library databases.

Research limitations/implications: The current study only used a questionnaire, a self-reported survey to collect data from the respondents of the study. Including other data collection instruments such as interviews would provide a holistic view of the data mining scenario from both the full-text articles and abstracts among the postgraduate students in Nigerian universities and this would make the generalisation of the study findings easier and more worthwhile.

Originality/value: Research on data mining either from full-text articles or abstracts were predominantly conducted in Advance countries. This study seems to be one of the pioneer studies in this area in Nigeria and Africa as a whole. It is the original idea by the author; and it is assumed that understanding the nature and context-related information in data mining by the postgraduate students is an original idea.

Full Text:




  • There are currently no refbacks.

Copyright (c) 2020 International Journal of Higher Education

International Journal of Higher Education
ISSN 1927-6044 (Print) ISSN 1927-6052 (Online) Email:

Copyright © Sciedu Press

To make sure that you can receive messages from us, please add the '' domain to your e-mail 'safe list'. If you do not receive e-mail in your 'inbox', check your 'bulk mail' or 'junk mail' folders.