Machine learning approaches cover several peoples’ daily life tasks including knowledge representation, data analysis, regression, classification, recognition, clustering, planning, reasoning, text recommendation, and perception. The machine learning approaches enable applications to understand with or without being directly programmed from previous data or experience. The machine learning techniques with current technologies provide a range of solutions, starting from vision-based solutions to text-generation solutions. To this end, this article presents a comprehensive knowledge of the approaches of machine learning including supervised, unsupervised, semi-supervised, reinforcement, and self-learning. The idea of the comprehensive review is to critically examine the roles performed by these aforementioned approaches, within current solutions, in terms of their weaknesses and strengths. Furthermore, within this study, a new comparative analysis is provided with a set of metrics such as data requirement, accuracy, complexity, interpretability, scalability, applications, and challenges. Thereafter, the implemented machine learning techniques are classified, and their key findings are examined. The comprehensive review shows that the machine learning approaches as a stand-alone or even within hybrid approaches can’t provide a suitable solution to meet all the aforementioned metrics.

Public service motivation (PSM) has been defined as a somebody's desire to advance community principles over committing facilities to the governmental sector. Whereas prosocial motivation (PM) is the desire of the total community to support individuals, PSM is a definite kind of prosocial motivation connected to public provision. High public service motivation is significantly linked with high levels of prosocial behavior between staffs in the governmental sector. PSM and PM have been proposed to affect work results. Although there is noteworthy study on PSM and PM, there is a lack of significant study on these motivations through detailed orientation to non-Western countries. This study examines the impact of PSM and PM on engagement, commitment, and organizational citizenship behavior (OCB) in the governmental sector in the Kurdistan Region of Iraq via using machine learning techniques. Data were gathered from 418 public workers from different cities in the Kurdistan Region. Machine learning procedures, with support vector machines (SVM), k-nearest neighbors (KNN), linear regression, and logistic regression, were used to analyze the data. The outcomes discovered that PSM assumes employee engagement, organizational commitment, and OCB between staffs. Moreover, the connection between PM and these variables is also positive, mentioning that both PSM and PM have impact on the whole performances and attitudes of staffs in the public sector setting. This study has inferences for worker motivation in the public sector, particularly for human resource departments and employees. Furthermore, it informs current discussions on the usage of motivational systems or practices in the governmental sector and their association to administrative efficiency.