Eduan Kotzé

Eduan Kotzé
University of the Free State | ufs · Department of Computer Science & Informatics

PhD

About

46
Publications
11,376
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
492
Citations
Introduction
Currently working towards developing technologies for extraction and analysis of sentiment from microblogging websites, using a combination of natural language processing (NLP), text mining and machine learning techniques.
Additional affiliations
March 2019 - present
University of the Free State
Position
  • Head of Department
January 2010 - December 2021
University of the Free State
Position
  • Professor (Associate)
January 2003 - December 2009
Free State Department of Health
Position
  • Principal Data Technologist
Education
January 2004 - March 2008
University of the Free State
Field of study
  • Data Warehousing, Business Intelligence, Action Research

Publications

Publications (46)
Conference Paper
Academic programmes at South African Higher Education Institutions have predominantly educated students in managing and storing data using relational database technology. However, this is no longer sufficient. South Africa as a country will need to educate more students to manage and process structured, semi-structured and unstructured data. The ma...
Article
Full-text available
South Africa is well known as a country characterised by racial and ethnic divisions, particularly for the divisions and conflicts between the white population and black population. This study uses the Twitter platform to analyse the discourse around the controversial town of Orania, a minority Afrikaner community that aims to preserve their Afrika...
Conference Paper
With the availability of open source intelligence systems, such as the Integrated Crisis Early Warning System (ICEWS), news stories are constantly being monitored and analyzed. However, with the increasing amount of data available on the Internet, automated methods such as machine learning can be used to quantify and speedup analysis. Although proj...
Article
Full-text available
With the growing amount of data available in the digital age, it has become increasingly important to use automated methods to extract useful information from data. One such application is the extraction of events from news sources for the purpose of a quantitative analysis that does not rely on someone needing to read through thousands of news art...
Article
With the advent of the information age, Open Source Intelligence (OSINT) has gained special prominence in the Intelligence Community (IC). However, the era of big data has brought numerous challenges in handling OSINT, in particular because big data comprise large volumes of unstructured data that are generated continuously. In this article, we dis...
Conference Paper
Full-text available
Our previous study on classification and detection of abusive language in South African social media space has shown the high prospect of surface level features and classical ma-chine learning models in terms of accuracy. However, much improvement is still needed in the aspect of F1-score. Therefore, the state-of-the-arts such as neural embeddings...
Article
Full-text available
From the point of view of systems and field theory, the value attached to a work of art, for example a literary text, is not only the result of the intrinsic characteristics of the text but also includes connections with institutions such as publishers, and factors like literary prizes, the value judgments of literary historians, of reviewers, and...
Article
Full-text available
Purpose Collaborative-based national cybersecurity incident management benefits from the huge size of incident information, large-scale information security devices and aggregation of security skills. However, no existing collaborative approach has been able to cater for multiple regulators, divergent incident views and incident reputation trust is...
Article
Full-text available
rom the late 19th century, and especially during apartheid (1948–1994), Afrikaans became inextricably tied with white people, white domination and apartheid. This association has persisted after 1994, and calls to preserve Afrikaans are often derided with claims that the preference for Afrikaans is also a preference for racial segregation. In such...
Article
Full-text available
Semi-supervised learning is a potential solution for improving training data in low-resourced abusive language detection contexts such as South African abusive language detection on Twitter. However, the existing semi-supervised learning methods have been skewed towards small amounts of labelled data, with small feature space. This paper, therefore...
Chapter
DSR is growing in acceptance as a research methodology in information systems for the design of innovative artefacts including design theory artefacts. Practical application of DSR can prove challenging when design theory artefacts are suggested for the first time originating from the field of practice. Within the described research context, this p...
Article
Full-text available
Humans and machines generate data at an alarming rate but still struggle to analyse and process this data fast enough. In order to meet this rising demand, business intelligence (BI) software firms are constantly incorporating new reporting or analytical functionalities in their software. At the same time, in order to be used optimally, they must e...
Article
Full-text available
Inligting word al duisende jare aangeteken deur van simbole wat klanke verteenwoordig, gebruik te maak, soortgelyk aan die moderne alfabet. Geleerdes is só toegelaat om oor lang afstande te kommunikeer, gebeurtenisse aan te teken, waarnemings te maak en om geskrewe kunsvorme te skep.
Article
Full-text available
In recent times, South Africa has been witnessing insurgence of offensive and hate speech along racial and ethnic dispositions on Twitter. Popular among the South African languages used is English. Although, machine learning has been successfully used to detect offensive and hate speech in several English contexts, the distinctiveness of South Afri...
Conference Paper
Full-text available
Major setbacks for detection of abusive South African tweets are inadequacy of annotated corpus and high cost of annotation, which semi-supervised learning solves. Semi-supervised learning techniques enhance training data by combining labelled and unlabelled data. However, existing approaches have skewed classification of unlabelled data towards la...
Article
Full-text available
Oopbronintelligensie het in die laaste paar dekades die dominante intelligensiedissipline geword. Die inligtingsontploffing het egter daartoe gelei dat geoutomatiseerde metodes aangewend moet word om inligting uit groot hoeveelhede data, wat gereeld in ’n ongestruktureerde formaat bestaan en deurlopend gegeneer word, te onttrek. Boonop het nuwe inl...
Article
Full-text available
Social media and related technologies have not only revolutionised communication between people, but also how business is conducted. The mountains of data generated by these technologies are of high value, and are often used for sentiment analysis. However, the implementation details of such systems often are omitted in literature. In an effort to...
Article
Full-text available
Die ontwikkeling van 'n koste-effektiewe en byderwetse multimedia digitale argief by EPOG in Orania 1 Burgert A. Senekal en Eduan Kotzé Burgert A. Senekal, Eenheid vir Taalfasilitering en Bemagtiging en Eduan Kotzé, Departement Rekenaarwetenskap en Informatika, Universiteit van die Vrystaat Opsomming Erfenisbewaring is sedert die begin van die mens...
Preprint
Full-text available
In this report, we present a study of eight corpora of online hate speech, by demonstrating the NLP techniques that we used to collect and analyze the jihadist, extremist, racist, and sexist content. Analysis of the multilingual corpora shows that the different contexts share certain characteristics in their hateful rhetoric. To expose the main fea...
Conference Paper
The way organizations deliver their business intelligence (BI) has changed substantially with the introduction of mobile technologies. Mobile BI, which incorporates mobile technologies and BI, is now used to enhance the decision making process in the organization. This study investigated information quality in mobile BI and some factors influencing...
Conference Paper
The demand for graduates with big data and data warehousing skills far exceeds the supply of students graduating with these skills. This paper addresses this problem by means of a pilot study in which big data topics were integrated into a classical data warehouse course at postgraduate level. Courses like this could be helpful in supporting hands-...
Article
Full-text available
Man and machine are generating data electronically at an astronomical speed and in such a way that society is experiencing cognitive challenges to analyse this data meaningfully. Big data firms, such as Google and Facebook, identified this problem several years ago and are continuously developing new technologies or improving existing technologies...
Conference Paper
Full-text available
The study investigates the contribution that social media makes to the environmental awareness of South Africans. It probes the environmental issues that South Africans are concerned with, their opinions regarding these issues, and attempts to determine whether social media contributes to positive action or reaction. A pilot study is reported on....
Article
Full-text available
The competitive environment today dictates that organisations must utilise their resources effectively and efficiently and also aim to provide their employees with the right information tools. Business Intelligence (BI) systems are known for their ability to increase organisational efficiency and effectiveness. This is achieved by providing decisi...
Conference Paper
Full-text available
Smart use of business intelligence (BI) can allow organizations to leverage the huge amounts of transactional data at their disposal and turn it into a powerful decision support mechanism that gives them competitive advantage. Despite the potential benefits of an effective BI system, the adoption and use of BI systems within the enterprise remains...
Conference Paper
Full-text available
Cloud computing is a rapidly evolving model that enables institutions to access computing resources as a service directly over the Internet. This model is radically different from current on-premise deployment strategies in part because it shifts the burden of owning (licensing) and operating (support and maintenance) the often complex computing en...
Article
Robust evidence of the effectiveness of task shifting of antiretroviral therapy (ART) from doctors to other health workers is scarce. We aimed to assess the effects on mortality, viral suppression, and other health outcomes and quality indicators of the Streamlining Tasks and Roles to Expand Treatment and Care for HIV (STRETCH) programme, which pro...
Article
In South Africa, many HIV-infected patients experience delays in accessing antiretroviral therapy (ART). We examined pretreatment mortality and access to treatment in patients waiting for ART. Cohort of HIV-infected patients assessed for ART eligibility at 36 facilities participating in the Comprehensive HIV and AIDS Management (CHAM) program in th...
Article
Full-text available
To assess differences in access to antiretroviral treatment (ART) and patient outcomes across public sector treatment facilities in the Free State province, South Africa. Prospective cohort study with retrospective database linkage. We analysed data on patients enrolled in the treatment programme across 36 facilities between May 2004 and December 2...
Conference Paper
Full-text available
South Africa is regarded as having the most severe HIV epidemic in the world. In response to this epidemic the South African Government started with the provisioning of Antiretroviral Therapy (ART) in the public health sector. Monitoring and evaluating the effectiveness of this ART programme is of the utmost importance. A data warehousing approach...
Article
The Acquired Immune Deficiency Syndrome epidemic, caused by the Human Immunodeficiency Virus, is a global crisis which threatens development gains, economies, and societies. Within sub-Saharan Africa, where the epidemic began the earliest and the HIV prevalence is the highest, African countries have death rates not seen before. In South Africa the...
Conference Paper
Full-text available
With a global HIV/AIDS epidemic, developing countries are facing an enormous challenge in combating the disease. Public health will be placed under severe pressure in providing treatment such as highly active antiretroviral therapy to all its HIV infected patients. This paper will describe the challenges involved in establishing a data warehouse to...

Network

Cited By

Projects

Projects (7)
Project
Document, research and make available data on South African Sign Language (SASL) place names.
Project
To investigate low-cost solutions for automatic detection of security events (such as protests, crime) in Southern Africa.