Doctoral Degrees (Information Systems and Technology)

Permanent URI for this collectionhttps://hdl.handle.net/10413/6926

Browse

Now showing 1 - 5 of 5

Fuzzy-based machine learning for predicting narcissistic traits among Twitter users.
(2022) Mursi, Japheth Kiplang’at.; Subramaniam, Prabhakar Rontala.; Govender, Irene.
Social media has provided a platform for people to share views and opinions they identify with or which are significant to them. Similarly, social media enables individuals to express themselves authentically and divulge their personal experiences in a variety of ways. This behaviour, in turn, reflects the user’s personality. Social media has in recent times been used to perpetuate various forms of crimes, and a narcissistic personality trait has been linked to violent criminal activities. This negative side effect of social media calls for multiple ways to respond and prevent damage instigated. Eysenck's theory on personality and crime postulated that various forms of crime are caused by a mixture of environmental and neurological causes. This theory suggests certain people are more likely to commit a crime, and personality is the principal factor in criminal behaviour. Twitter is a widely used social media platform for sharing news, opinions, feelings, and emotions by users. Given that narcissists have an inflated self-view and engage in a variety of strategies aimed at bringing attention to themselves, features unique to Twitter are more appealing to narcissists than those on sites such as Facebook. This study adopted design science research methodology to develop a fuzzy-based machine learning predictive model to identify traces of narcissism from Twitter using data obtained from the activities of a user. Performance evaluation of various classifiers was conducted and an optimal classifier with 95% accuracy was obtained. The research found that the size of the dataset and input variables have an influence on classifier accuracy. In addition, the research developed an updated process model and recommended a research model for narcissism classification.
Genetic algorithm based prediction of students' course performance using learning analytics.
(2024) Raghavjee, Rushil.; Subramaniam, Prabhakar Rontala.; Govender, Irene.
Learning Analytics (LA) can play a key role in understanding students’ learning and academic performance. By identifying poorly performing students early, LA can also be used to identify students who are at risk of dropping out of programmes. This enables academic advisors to intervene early and provide help to ensure students stay on track and succeed in their studies. Hence, LA is becoming a common trend in education particularly in higher education. Previous studies of LA have not dealt with specific courses in information systems and information technology. Therefore, the aim of this study was to develop a model for the application of LA to different courses with the discipline of Information Systems and Technology using various data sources. This study used the design science research approach to help towards solving the problem of understanding students’ learning and performance in Higher Education Institutions (HEIs). Multiple data sources were used. The data that was obtained was pre-processed using MS Excel. Thereafter, the WEKA tool was used in the analysis of the data and prediction of performance. Decision tree, Random Forest and genetic-based algorithms were used to develop prediction models for each of the courses in the discipline of Information Systems and Technology at the University of KwaZulu-Natal. The study also resulted in the development of an integrated dataset for the discipline of Information Systems and Technology in higher education and a process model for the implementation of LA in a specific discipline. The involvedness of the data allows future researchers to continuously improve/evolve the area of LA. This study should, therefore, be of value to LA practitioners wishing to implement LA to courses within other disciplines as well.
The interpretation and application of triangulation in information systems research.
(2020) Mutinta, Given Chigaya.; Govender, Irene.; McArthur, Brian Walter.
Scholars argue that a single research method is inadequate to investigate a complex phenomenon. As a result, there is growing interest in academic communities in the practicability of mixing research techniques in a process of triangulation. The purpose of this study was to investigate the interpretation and application of triangulation within the disciplines of information systems (IS) at four universities in South Africa; the University of KwaZulu-Natal, the University of Cape Town, the University of the Witwatersrand, and Stellenbosch University. This study employed the exploratory and descriptive research designs, and mixed methods. The target population were academic staff in the IS disciplines. Census and purposive sampling were used to select participants for the quantitative and qualitative study respectively. A sample size of fifty (50) and eight (8) academics was drawn for the quantitative study and qualitative study respectively. Data was collected using document collection, questionnaires, and in-depth interviews. In-depth interviews and documents were analysed using thematic analysis technique. Questionnaires were analysed using the Statistical Package for the Social Sciences (SPSS) version 22.1. The findings show that all (100 per cent) respondents were aware of triangulation. Data source triangulation (100.0 per cent) and methodological (82.4 per cent) are the most known types of triangulation. Methodological (90.2 per cent), investigator (67.0 per cent), data source (65.6 per cent), space (60.8 per cent), theory (52.9 per cent), time (41.1 per cent) and analyst (14.0 per cent) triangulation are the most used in this order. In spite of high respondents’ high levels of knowledge of triangulation, the seven types of triangulation are mainly used to validate research findings and explain research problems. There is thus a gap between the knowledge of triangulation and application of triangulation. IS academics find it easy to use data source (65.6 per cent), time (45.3 per cent), methodological (37.0 per cent), investigator (35.0 per cent), time (40.0 per cent), time (29.0 per cent), and space triangulation (23.5 per cent) in this order. Intradisciplinary triangulation is the most used than interdisciplinary triangulation. The findings indicate that academics with doctorates find it easier to use different types of triangulation than those with master’s degrees. The findings show that the frequently used type of triangulation is data source (19.0 per cent) and methodological (14.0 per cent). Largely, the study suggests that triangulation should be interpreted as Data source, Investigator, Theoretical, Methodological, Analyst, Space, and Time (DITMAST) triangulation, and to be used to Validate findings, Explain research problem, Enrich research instruments, and Refute findings (VEER). There is need to empower IS academics with knowledge on the interpretation of the different types of triangulation (DITMAST) and their application (VEER) in research.
Towards an integrated e-government framework for housing and urban development agencies: a case study in Lagos state Nigeria.
(2017) Mosud, Yinusa Olumoye; Govender, Irene.
The urgent demand for efficient and effective delivery of housing and urban development services, especially building permit services to facilitate housing development necessitated this study. Housing and Urban Development Agencies (HUDAs) are important government service delivery sectors, where the implementation of an integrated electronic government (e-Government) is a necessity. In the present Lagos State of Nigeria, anecdotal evidence and insight indicates that the process of acquiring development permits has proven extremely difficult, whereby citizens have to consult diverse agencies before obtaining their permits. This condition has created gaps between the citizens’ expectations and services rendered by the Lagos State HUDA. Consequently, this study proposes a conceptual framework for integrating the Lagos State Government HUDA. The framework is underpinned by technology-organisationenvironment model and complemented with some elements of drivers-barriers and threequarter moon models. The study adopts a case study approach which focuses on government to government and government to citizens in the Lagos State HUDA. Moreover, an in–depth investigation of the agencies’ information technology was conducted utilising both primary and secondary sources. The main data collection instrument used was interview and complemented with questionnaire. From the research findings, the factors (technological, organisational and environmental), the perceptions (barriers, benefits and risk) as well as the major stakeholders and their activities influencing integrated e–Government implementation in the Lagos State HUDA were determined. These were compared with those expounded in the existing literature, although some were specifically applicable to the Lagos State HUDA context. Based on the thematic analysis of the qualitative data and the statistical analysis of the quantitative data, some factors were newly derived while others were validated from the research findings. These factors were used to examine and validate the conceptualised integrated e-Government framework statistically. Hence, an innovative model that provides a holistic perspective for the implementation of integrated e-Government in the Lagos State (i-eGovF4Lag) HUDA was developed. The framework would contribute to a new generation of knowledge in the electronic government field and also help the policy makers to identify and proffer solutions to the challenges hindering the successful implementation of ICT initiatives in Nigeria and other developing nations.
Towards improving teaching and learning in colleges of education using mobile learning – the Nigerian perspective.
(2017) Chaka, John Gyang.; Govender, Irene.
The teaching and learning conditions, for example classrooms, learning materials, and manpower in colleges of education in Nigeria, which were established with a mandate to train foundation-level (primary school) teachers, are grossly inadequate. Compounding the situation is the high population growth and the high level of insurgency in Nigeria. The result is poor access to education, inadequate training of teachers and an overall negative effect on nation building. This study considers m-learning (mobile learning), as one viable way of addressing some of the challenges. To explore this possibility, the study is conducted in two stages. A mixed methods approach is employed across the entire study. The main research strategies used are surveys and interviews while observations are used in some cases. The preliminary stage investigates the perceptions of stakeholders or possible factors that may influence their intention to use m-learning. Study samples of 375 and 30 were used for the quantitative and qualitative components respectively. First, the preliminary study explored the experiences and usage of mobile devices by stakeholders, thereafter, their perceptions or factors that may have some influence on their intention to use mobile learning and social networking sites were ascertained. The second stage tests the implementation of the m-learning approach in four courses in colleges of education using study samples of 330 and 15 for the different components. While the preliminary study is guided by UTAUT (a subset of the conceptual framework), the second stage is underpinned by the entire conceptual framework derived from UTAUT, information systems success model and educational use of the Facebook model. Descriptive statistics and structural equation modelling (SEM) are applied to analyse the quantitative data while the qualitative data is analysed using content analysis aided by Nvivo. Findings from the preliminary stage reveal that stakeholders are positive about mobile learning, signalling their readiness to accept the technology. In the final stage, the study reveals that m-learning significantly improves the teaching and learning conditions in colleges of education, specifically by reducing the inadequacies of physical facilities, and by improving the reading culture and performance of students. The results further indicate that most of the stakeholders are satisfied with the benefits of m-learning and wish to continue using the technology. The research also contributes to theory and practice, extending m-learning implementation literature, through the development of an m-learning implementation model, which will be of value to colleges of education in Nigeria and beyond.

Browse

Browsing Doctoral Degrees (Information Systems and Technology) by Author "Govender, Irene."