Journal of Information and Organizational Sciences

361-374

Authors: Tarig Mohamed Ahmed

The most important challenge facing modern organizations is to keep their employees as valuable assists. Employee turnover is one of these challenges. This paper aims to develop a novel model that can help decision-makers to classify the problem of Employee Turnover. The proposed model is based on machine learning algorithms. The model was trained and tested by using a dataset that consists of 1470 records and 25 features. To develop the research model, many experiments had been conducted to find the best one. Based on implementation results, the Neural Network algorithm is selected as the best one with an Accuracy of 84% and AUC (ROC) of 74%. By validation mechanism, the model is acceptable and reliable to help origination decision-makers to manage their employees in a good manner and setting proactive plans to keep them. Besides the model, three important features should be dealt with carefully as Over Time, Job Level, Monthly Income.

399-409

Authors: Yuriy Golchevskiy; Andrei Yermolenko

The Internet has become an independent global electronic environment for economic activity, which for many companies has come to the forefront, not only complementing but also replacing the business methods used for decades. Almost any company, linking its activities to the Internet, develops and maintains its representation in the form of a corporate portal or website. Sites become more functional, more beautiful and informative over time, but many managers forget or do not pay due attention to such an important element of the site as feedback from external and internal contractors. This article presents the effectiveness of using feedback on specific examples in a simple and straightforward way, and gives an overview of the different forms of organisation of such communication, with an indication of possible tools for their implementation.

435-449

Authors: Vladyslav Yaloveha; Daria Hlavcheva; Andrii Podorozhniak

Deep learning approaches are applied for a wide variety of problems, they are being used in the remote sensing field of study and showed high performance. Recent studies have demonstrated the efficiency of using spectral indexes in classification problems, because of accuracy and F1 score increasing in comparison with the usage of only RGB channels. The paper studies the problem of classification satellite images on the EuroSAT dataset using the proposed convolutional neural network. In the research set of the most used spectral indexes have been selected and calculated on the EuroSAT dataset. Then, a novel comparative analysis of spectral indexes was carried out. It has been established that the most significant set of indexes (NDVI, NDWI, GNDVI) increased classification accuracy from 64.72% to 84.19% and F1 score from 63.89% to 84.05%. The biggest improvement was obtained for River, Highway and PermanentCrop classes.

473-494

Authors: Tamara Ređep; Goran Hajdin

This paper reviews the literature and analyzes the research topics on the use of augmented reality technology in education with possible integration of game elements, in order to obtain a synthesis of previous knowledge related to the topic in the period from 2010 to 2020. Fifty-two papers describing different aspects of augmented reality used in the field of education were selected for the analysis. The main conclusions of the systematization and synthesis were: a) five basic thematic categories were identified; b) 2019 was recognized as the year with the largest publication of papers; c) the use of augmented reality in teaching activities, and especially with game elements, improves student efficiency, stimulates attention and interest, brings improvements in collaboration and perception of fun, improves teaching and learning processes and in general encourages innovation and improvement through educational technology.

513-533

Authors: Sonja Nidogon Višnjić; Neven Vrček

Digital transformation (DT) of agencies for students`part time jobs in the Republic of Croatia (RC) began to be mentioned through the adoption of the Act of student activities (Act). The work of students in the Republic of Croatia is regulated by the Act [1], which provides the legal basis for the DT system of mediation in employment. The Act and the Ordinance oblige the mediator to keep all records in electronic form and define the possibility of issuing student contracts in electronic form, but up to now this form of contract has not been experienced in practice [1], [2]. The distinction between digitization and DT in part led to the fact that the electronic student contract currently implies the issuance of an online student contract, which was not signed by an advanced electronic signature. Changes in business caused by COVID-19 contributed to greater utilization of existing online contracts and pointed to inconsistencies in the work of intermediaries. The aim of this paper is to present, based on a literature review and analysis of the existing situation through the case study, the conceptual model of the DT system for mediation in employment and to test the digital maturity of the current system. The scientific contribution of the paper is in presenting a model that can be implemented in the daily practice of all students employment agencies, while the social contribution is reflected in the attempts of DT public institutions that should be used as an example to the private sector.

553-565

Authors: Andrej Šorgo; Mateja Ploj Virtič; Kosta Dolenc

Two online surveys among 1105 university students and 656 employees were conducted with the inclusion of the construct Personal Innovativeness in the domain of Information Technologies (PIIT). After calculating descriptive statistics, statistically significant differences between personal innovativeness of university students and teachers were sought by the application of one-way ANOVA. The first and most important finding was that average perceived PIIT of teachers and students falls around the middle of the seven-point scale, which cannot be regarded as a plausible predictor of upgrading the University as an Innovative Ecosystem. The second was that university teachers scored higher than their students, a situation that could produce an expectancy conflict between those who want to work in an innovative way and those who would prefer study by the book. Teaching assistants, who should belong to the generation of digital natives, are only slightly more innovative than university teachers, who can be regarded as digital immigrants. Assuming that innovativeness can be upgraded by learning, means that efforts should be made by University Management to encourage and support Personal Innovativeness (and other creativities, as well) as a preferred teaching practice.

579-599

Authors: Damir Dobrinić; Iva Gregurec; Dunja Dobrinić

This paper aims to investigate Croatian consumers' attitudes about mobile messenger chatbots (MMC) and their propensity to use them. The proposed conceptual model is based on the Technology Acceptance Model (TAM) and Innovation Diffusion Theory (IDT). The research was conducted through an anonymous survey questionnaire available on the social network Facebook. The empirical research results show that perceived usefulness, perceived ease of use, compatibility, and attitude towards mobile advertisements are statistically significantly related to attitude towards mobile messenger chatbots. No negative correlation was found between internet privacy concern and consumer attitudes about mobile messenger chatbots. A positive correlation was found between attitude towards using mobile messenger chatbots and behavioral intention. In addition to the scientific contribution in better predicting chatbots' acceptance as a communication and promotional tool, the research results will also help marketing experts design advertising campaigns via mobile messenger chatbots.