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.

1-20

Authors: Mario Jadrić; Maja Ćukušić; Tea Mijač

Following the results of recent studies on the creative use of smart technologies in urban and university settings, there is a growing number of promising research areas under smart university as an umbrella term. Starting from the differentiation between six standard “smart” dimensions in the university, the paper focuses on one smart university feature in particular – it explores the level and the relation of smart governance to the perception of university management, fellow students, and Perceived External Prestige (PEP) as antecedents of university affective commitment. The paper presents the results of a multivariate analysis based on the feedback from over 400 university first-year students. While the effect of Smart governance on the Perception of university management is found to be positive and significant, the effect of Perception of university management on Students' university commitment is low and not significant in the given context.

39-53

Authors: Jasmina Đurašković; Dejan Viduka; Marina Gajić - Glamočlija

The development and use of information and communication technologies (ICTs), and in particular the Internet, have changed the way businesses operate in the last twenty years, providing a number of new opportunities for improving innovation and competitiveness. Today, modern ICT is considered to be the basis for the development of a knowledge society, in which the concept of e-government plays a special role. The main goal of this paper was to examine the perceptions of business users, in terms of perceived barriers and benefits achieved, from the use of electronic public administration services. The survey included 500 companies with the highest business income in Serbia. The data collected were analyzed using Pearson’s correlation coefficient, Mann Whitney’s test and Kruskal-Wallis test. The results of the research showed that the level of acceptance of electronic services is still lower than expected, given the volume of services offered. Also, this study pointed to the need to raise the level of awareness of businesses about e-government services, as well as the need to improve the quality of electronic services, in terms of complete digitization, alignment with enterprise requirements and regular updating of data.

77-94

Authors: Alexander V. Rubtsov; Violetta V. Levshina; Svetlana V. Mamaeva; Ludmila N. Khramova; Igor V. Khramov

This study's subject represents the processes of functioning of information flows in a network information system through the use of fuzzy sets. It considers the possibilities of fuzzy sets in the information flows distribution problems of the Network Information System by the development of mathematical tools. In the theoretical part of the study, the main issue was the description of the fuzzy approach. In the empirical part of the study, the main concern was finding out the reasons for the fuzzy approach's advantages. The main results of the study: proof of the identity between the functioning of the analytical data; held the solution of the optimization problem based on the formulated analytical models; comparison of the usage of fuzzy logic with a different statistical method; demonstrated the advantage of fuzzy approach in modeling processes network information system. The results can be applied in the field of information systems and technologies.

115-135

Authors: Weli Weli

The end-user computing satisfaction model (EUCS) has been widely used in previous studies, and Enterprise Resource Planning. Therefore, Enterprise Resource Planning (ERP) System, need to be developed in accordance with cloud computing that dominate current information technology devices. This study was carried out to test the expansion of the EUCS model in a cloud-based ERP system. Therefore, the purpose of this research is to re-examine the validity and reliability of the computer application satisfaction model and its relationship with user performance in cloud-based ERP system. The overall satisfaction variable is added as a mediation between the satisfaction model and user performance. Data was collected through snowball sampling with a questionnaire distributed to the cloud-based ERP users. Additionally, data processing was conducted using the Second-order concept in structural equation modeling with the Partial Least Square approach. Since data processing using WarpPLS confirmed the validity and reliability of the model and all relationships between variables, this research contributes theoretically to the study of end-user satisfaction from information technology applications. Its final section describes the limitations and opportunities for future research.

171-221

Authors: Ahmad H. Ababneh; Joan Lu; Qiang Xu

The traditional statistical approach in synonyms extraction is time-consuming. It is necessary to develop a new method to improve the efficiency and accuracy. This research presents a new method in synonyms extraction called Noun Based Distinctive Verbs (NBDV) that replaces the traditional tf-idf weighting scheme with a new weighting scheme called the Orbit Weighing Scheme (OWS). The OWS links the nouns to their semantic space by examining the singular verbs in each context. The new method was compared with important models in the field such as the Skip-Gram, the Continuous Bag of Words, and the GloVe model. The NBDV model was manipulated over the Arabic and English languages and the results showed 47% Recall and 51% Precision in the dictionary-based evaluation and 57.5% Precision in the human experts’ evaluation. Comparing with the synonyms extraction based on tf.idf, the NBDV obtained 11% higher recall and 10% higher precision. Regarding the efficiency, we found that on average, the synonyms extraction of a single noun requires the process of 186 verbs and in 63% of the runs; the number of singular verbs was less than 200. It is concluded that the developed method is efficient and processes the single run in linear time.

243-265

Authors: Syed Muhammad Fahim; Syeda Misbah Inayat; Syed Muhammad Rafay Zaidi; Daniyal Ahmed; Ramish Hassan; Syed Zulfiqar Ali

This paper aims to find out the extent to which organizational culture and intellectual capital influence the textile industry’s business performance in Pakistan. The study uses causal and explanatory research design. Several 200 textile industry employees participated in this survey, selected as the study sample using the purposive sampling technique. The study detects that both organizational and intellectual capital directly impact the textile firms’ business performance. However, the impact of intellectual capital on business performance is more substantial than that of organizational culture. The mediating effect of technological innovation in the relationship between organizational culture and business performance is also supported. The study can be used by the textile industry managers to set up policies on how to improve business performance in the textile firms. The study also fills the literature gap as prior studies do not have worked on the mediating aspect of technological innovation.

287-308

Authors: Falah Al-akashi; Diana Inkpen Inkpen

With the rapidly growing amount of information on the internet, real-time system is one of the key strategies to cope with the information overload and to help users in finding highly relevant information. Real-time events and domain-specific information are important knowledge base references on the Web that frequently accessed by millions of users. Real-time system is a vital to product and a technique must resolve the context of challenges to be more reliable, e.g. short data life-cycles, heterogeneous user interests, strict time constraints, and context-dependent article relevance. Since real-time data have only a short time to live, real-time models have to be continuously adapted, ensuring that real-time data are always up-to-date. The focal point of this manuscript is for designing a real-time web search approach that aggregates several web search algorithms at query time to tune search results for relevancy. We learn a context-aware delegation algorithm that allows choosing the best real-time algorithms for each query request. The evaluation showed that the proposed approach outperforms the traditional models, in which it allows us to adapt the specific properties of the considered real-time resources. In the experiments, we found that it is highly relevant for most recently searched queries, consistent in its performance, and resilient to the drawbacks faced by other algorithms.

329-349

Authors: Branislav Mados; Zuzana Bilanová; Ján Hurtuk

Lossless data compression algorithms can use statistical redundancy to represent data using a fewer number of bits in comparison to the original uncompressed data. Run-Length Encoding (RLE) is one of the simplest lossless compression algorithms in terms of understanding its principles and software implementation, as well as in terms of temporal and spatial complexity. If this principle is applied to individual bits of original uncompressed data without respecting the byte boundaries, this approach is referred to as bit-level Run-Length Encoding. Lightweight algorithm for lossless data compression proposed in this paper optimizes bit-level RLE data compression, uses special encoding of repeating data blocks, and, if necessary, combines it with delta data transformation or representation of data in its original form intending to increase compression efficiency compared to a conventional bit-level RLE approach. The advantage of the algorithm proposed in this paper is in its low time and memory consumption which are basic features of RLE, along with the simultaneous increase of compression ratio, compared to the classical bit-level RLE approach.