AJIC Issue 30, 2022

Permanent URI for this collection

https://hdl.handle.net/10539/34917

Browse

Recent Submissions

Now showing 1 - 5 of 10
  • No Thumbnail Available
    Item
    AJIC Issue 30, 2022 - Full Issue
    (LINK Centre, University of the Witwatersrand (Wits), Johannesburg, 2022-12-23)
    Articles on YouTube micro-celebrities; a word embedding trained on news data; using machine learning to predict low academic performance; radio, mobile communications, and women’s empowerment; assessment of website quality; ABET accreditation of computer science programmes; and national digital transformation policy and practice.
  • No Thumbnail Available
    Item
    AJIC Issue 30, 2022 - Full Issue - Print-on-Demand
    (LINK Centre, University of the Witwatersrand (Wits), Johannesburg, 2022-12-23)
    Articles on YouTube micro-celebrities; a word embedding trained on news data; using machine learning to predict low academic performance; radio, mobile communications, and women’s empowerment; assessment of website quality; ABET accreditation of computer science programmes; and national digital transformation policy and practice.
  • No Thumbnail Available
    Item
    Roles played by Nigerian YouTube micro-celebrities during the COVID-19 pandemic
    (LINK Centre, University of the Witwatersrand (Wits), Johannesburg, 2022-12-23) Agbese, Aje-Ori
    In 2020, during the COVID-19 pandemic, Nigerian social media micro-celebrities were prominent players in the dissemination of information. This study examines the roles that one group of Nigerian micro-celebrities, YouTube video bloggers (vloggers)—also known as “YouTubers”—played during the pandemic. The research analysed the contents of COVID-19-themed videos that 15 popular Nigerian YouTubers posted on their channels between 29 February and 5 August 2020. The study was guided by the two-step flow of communication theory, in terms of which information first flows from mass media to opinion leaders, who then, in the second step, share the information with their audiences. The study found that all 15 YouTubers played positive roles as opinion leaders—by providing health and safety information on COVID-19, challenging myths, and educating audiences through entertainment. Only two of the YouTubers studied were found to have shared some information that misinformed their audiences about the virus and how to fight it. The study therefore concluded that Nigerian YouTubers, as opinion leaders, can be important allies to governments and organisations when health crises arise in the country.
  • No Thumbnail Available
    Item
    A word embedding trained on South African news data
    (LINK Centre, University of the Witwatersrand (Wits), Johannesburg, 2022-12-23) Mafunda, Martin Canaan; Schuld, Maria; Durrheim, Kevin; Mazibuko, Sindisiwe
    This article presents results from a study that developed and tested a word embedding trained on a dataset of South African news articles. A word embedding is an algorithm-generated word representation that can be used to analyse the corpus of words that the embedding is trained on. The embedding on which this article is based was generated using the Word2Vec algorithm, which was trained on a dataset of 1.3 million African news articles published between January 2018 and March 2021, containing a vocabulary of approximately 124,000 unique words. The efficacy of this Word2Vec South African news embedding was then tested, and compared to the efficacy provided by the globally used GloVe algorithm. The testing of the local Word2Vec embedding showed that it performed well, with similar efficacy to that provided by GloVe. The South African news word embedding generated by this study is freely available for public use.
  • No Thumbnail Available
    Item
    Using machine learning to predict low academic performance at a Nigerian university
    (LINK Centre, University of the Witwatersrand (Wits), Johannesburg, 2022-12-23) Ekubo, Ebiemi Allen; Esiefarienrhe, Bukohwo Michael
    This study evaluates the ability of various machine-learning techniques to predict low academic performance among Nigerian tertiary students. Using data collected from undergraduate student records at Niger Delta University in Bayelsa State, the research applies the cross-industry standard process for data mining (CRISP-DM) research methodology for data mining and the Waikato Environment for Knowledge Analysis (WEKA) tool for modelling. Five machine-learning classifier algorithms are tested—J48 decision tree, logistic regression (LR), multilayer perceptron (MLP), naïve Bayes (NB), and sequential minimal optimisation (SMO)—and it is found that MLP is the best classifier for the dataset. The study then develops a predictive software application, using PHP and Python, for implementation of the MLP model, and the software achieves 98% accuracy.