Use of Data Mining Tools in Determining Patrons’ Information Needs for Collection Development in Selected Academic Libraries in Kenya
Loading...
Date
2025-11
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Kenyatta University
Abstract
Data mining is defined as the process of identifying and extracting useful information from a large pool of raw data. In context of this study, data mining tools refer to the techniques, strategies, channels used to collect raw data into the data warehouse. Though data mining tools have been in use for a considerably long time, it has been emphasized and largely used in commercial settings: manufacturing, banks, the health sector and the customer service industries in order gather feedback from clients in bid to offer satisfactory services to their clients. The studies lacked information on how raw data was obtained and from whom. The studies reviewed also had a glaring deficiency on the use of data mining tools by academic libraries for developing a patron driven collection. This study therefore sought to look into the application of data mining tools in the collection development process and focused on the aspect of data mining at the point of collecting raw data, rather than analyzing the data to form patterns. The purpose of this study was to evaluate how academic libraries embrace and utilize data mining tools in order to build a collection based on the information needs of its users. The research was based on the following objectives: to establish various data mining tools available in libraries, to assess librarians’ awareness of the existence of data mining tools, to determine contribution of postgraduate students in the collection development process by use of data mining tools and to assess the current acquisition processes in use. The study focused on two academic libraries; Kenyatta Univeristy and Jomo Kenyatta University of Agriculture and Technology. Data was collected from the university librarian, acquisition librarians and postgraduate students from each university. The university librarians and acquisition librarians were purposively selected and Slovins’ formula was used to derive the sample population for Post Graduate students. Data was collected using interviews for the university librarians and questionnaires for acquisition librarians and Post Graduate students. The data collected was analysed using the Statistical Package for Social Sciences, and presented in form graphs, tables, and charts. The study derived the following findings: that data mining tools were available in the libraries, librarians were aware of the existence of various data mining tools, the Post Graduate students were not directly involved in the collection development process and that the libraries relied heavily on curriculum requirements and suggestions from the faculty during selection and acquisition of information resources. The study recommended that libraries should sensitize their staff on the use of data mining tools for collection development. The study further recommended that librarians should capitalize on their patrons’ input where data mining tools play a significant role in order to achieve a patron driven collection.
Description
A Research Project Submitted in Partial Fulfillment of the Requirements for the Award of the Degree of Master of Science (Library and Information Science) In the School of Pure and Applied Sciences Kenyatta University, November 2025.
Supervisor
1. Dr. Rose Njoroge