Student publications at SAICSIT 2019

In September 2019 four projects were presented at the 2019 Annual Conference of the South African Institute for Computer Scientists and Information Technologists, held in Skukuza, South Africa. All for projects are to be published in the conference proceedings and are available through the ACM.

Staff and students at SAICSIT 2019

An exploratory investigation of online and offline social behaviour among digital natives

In response to calls for IS researchers to investigate how digital natives are using information and communication technologies to shape their interpersonal interactions, an exploratory, survey-based study was conducted to investigate patterns of online social behaviour on two popular SNSs (Facebook and Instagram) and, on this basis, compare their online and offline social behaviour. To capture online social behaviour a novel typology involving three high-level interactions — producing, consuming, and reacting— was proposed. The investigation found that, among digital natives, Instagram is used more frequently than Facebook, with consumptive behaviour on Instagram occurring most frequently, and productive behaviour on Facebook occurring least frequently. While online social behaviour was found to positively relate to offline socialisation, personality traits were found to account for a larger proportion of the variance in offline social behaviour than online actions. The findings are of particular relevance to those seeking to understand associations between behaviour online and behaviour offline. Moreover, the typology introduced is likely to be useful in a variety of contexts.

Does automation influence career decisions among South African students?

The potential impact of rapidly advancing automation technologies on the demand for human labour has emerged as a prominent discourse in mainstream and academic media. In this study we advance this line of inquiry by determining the extent to which automation influences the career decisions of university students. 935 undergraduate students at a large, research-oriented university completed a survey which addresses level of awareness of automation, beliefs about automation, as well as the factors and sources of influence which impact career decisions. Our findings suggest that, while most students perceive themselves to be well informed about automation, and generally believe that machines will displace human labour, they do not consider their own future occupations to be susceptible to automation. Accordingly, few students consider automation as a factor when making career decisions.

A Computational Analysis of News Media Bias: A South African Case Study

News media in South Africa is assumed to be unbiased and objective in their reporting of the news. Indeed, editors are required to uphold an objective and balanced view with no favour to external political or corporate interests. This assumption of objectivity is tested on a large scale by computationally analysing 30 000 articles published by five media houses: News24, SABC, EWN, ENCA, and IOL. Using topic modelling, 38 topics are extracted from the corpus, and sentiment is computed for each topic. The study highlights various cases of both over and under-reporting by media houses on particular topics. We also identify various tonality biases by media houses.

Cross-Sample Community Detection and Sentiment Analysis: South African Twitter

This study investigates the persistent communities on South African Twitter across 24 datasets that have been collected since 2014. It also analyses the sentiment of the identified communities towards each other, as well as the sentiment the community shares with itself. To perform this analysis, 24 datasets were aggregated, cleaned and an iterative approach to community detection was used to accurately map the South African communities. The procedure identified 18 communities, 15 of which were found to be persistent across all datasets. The overall sentiment calculated across the dataset resulted in 16.1% tweets classified as neutral, 41.6% classified as positive and 40.3% of tweets classified as negative. Sentiment was aggregated to community level to investigate the polarity of interactions between these communities.

Comments are closed.