MACHINE LEARNING ALGORITHMS AS PREDICTORS OF USER NEEDS IN LIBRARY SYSTEMS IN SOUTH EAST NIGERIA

Abstract

The study investigated machine learning algorithms as predictors of user needs in library systems in South-East, Nigeria. Two research questions and two null hypotheses guided the study. A survey design was adopted for the study. A sample of 120 study participants from two Universities in South-East were used for the study. An instrument captioned Machine Learning Algorithms as predictors of user Needs in Library Systems (MLAPUNLS) was self-designed and used for data collection. The first section of the instrument focused on demographic variables; while the second part addressed the questionnaire items. The response options include, Strongly Agree, Agree, Disagree and Strongly Disagree. The validity of instrument was ascertained by experts from the department while the reliability index of 0.78 was obtained using test-retest method. The data collected from research questions were analyzed using mean and standard deviation, while the hypotheses were tested with t-test statistics at 0.05 level of significance. Major findings of the study revealed that machine learning algorithms predicts user needs in library systems by analyzing user behavior and offering personalized services to users. It was recommended that library staff should be encouraged to attend trainings to improve their skills.