Repository logo
 

Faculty of Accounting and Informatics

Permanent URI for this communityhttp://ir-dev.dut.ac.za/handle/10321/1

Browse

Filters

2019 - 201912020 - 20241

Settings

Has files: YesSubject: search.filters.subject.Twitter

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Evolving a framework to observe and analyse customer experience on the Twitter platform using machine learning techniques
    (2024) Moodley, Thaneshni; Thakur, Surendra
    Retailers have become more focused on retaining and turning existing customers into longterm clients because retailers have become more competitive, customers more demanding, and competitors more aggressive. The 2020 COVID-19 pandemic has forced a transformation for retailers. Within months, a revolution has taken place, constituting major changes to how consumers view cash, how they shop online and what they expect from retailers as part of a positive buying experience. Consumers increasingly expect retailers to create a seamless customer experience. This often means leaning on digital capabilities to create a seamless, omni-channel experience by linking different aspects of the customer shopping experience. The usage of big data analytics has primarily been implemented outside of South Africa to better understand customer connections and experiences, highlighting a noticeable research gap in South Africa. It has been proven to be an effective tool for retailers in predicting customer behaviour. There is a need to reduce the complexities in understanding which are the most appropriate machine learning techniques for sentiment analysis of online customer experience and to capitalise on development. Thereafter, online retailers are better equipped to tailor machine learning tools to craft analytical tools. Given the massive migration to online transactions, this work presents a rigorous analysis of social media posts, which is paramount for modern-era retailers. Businesses can use sentiment analysis to determine how well their brand is performing in the marketplace, learn more about the attitudes of their customers and determine whether their items receive more positive or negative feedback. A longitudinal study was adopted to analyse a dataset of retail-related tweets for the identification of customer complaints using a sentiment analysis hybrid approach, which is a combination of lexicon and machine learning approaches. A conceptual framework was developed to observe and analyse customer experiences on the Twitter platform using machine learning techniques. The framework encompasses components such as data preparation, natural language processing pre-processing techniques, calculating sentiment using sentiment lexicon and ML techniques, and thereafter a selection of the best-performing machine learning technique for sentiment analysis within the developed conceptual framework. The extracted dataset contains 240 000 tweets posted between 01 January 2017 and 31 January 2019, out of which 27 233 tweets were selected for the study. Natural language pre-processing techniques were applied to the dataset, including tokenisation, stemming, lemmatisation, part-of-speech tagging, and name-of-entity recognition. Supervised and deep machine learning gave the best results of 61.75 and 60.25. This study has identified deep learning as a good technique for sentiment analysis when NLP pre-processing methods are done in a certain order. A study on analysing retail complaints posted on the Twitter platform using a sentiment analytic framework has not been done in South Africa before. This study has proven that the sentiment analysis hybrid approach is highly capable of analysing social media data.
  • Thumbnail Image
    Item
    A longitudinal sentiment analysis of the #FeesMustFall campaign on Twitter
    (2019-04-29) Khan, Yaseen; Thakur, Surendra
    The #FeesMustFall campaign began in 2015 to lobby government to provide students with free university education in order to redress past imbalances. It rapidly progressed to become a widespread national phenomenon that attracted international attention and sympathetic support. However, certain unsavoury incidents marred the campaign and attempted to derail it from achieving its goals. The campaign did reach many of its targets with the South African government eventually announcing free education for the poor and working class in December 2017. #FeesMustFall has been well documented and researched, however, no literature offered a quantitative insight into the opinions of social media users during this campaign, although a unique feature of #FeesMustFall was leveraging social media platforms to coordinate the campaign. This study addresses this gap by undertaking a longitudinal sentiment analysis of textual conversations expressed on the Twitter social media platform. This longitudinal study analyses the Twitter #FeesMustFall campaign through the acquisition of 576 583 tweets posted between 15 October 2015 and 10 April 2017. These tweets were pre-processed and cleaned by removing exact duplicates and unintelligible data. The research method to analyse the “cleaned” #FeesMustFall data utilises, inter alia, descriptive statistics, sentiment analysis using a natural language programming (NLP) approach called Valence Aware Dictionary sEntiment Reasoner (VADER) and code written in Python. VADER is a lexicon rule-based sentiment analysis tool particularly suited to social media. To detect multiple changes in this large historical dataset, the Change Point Analysis method (CPA) is applied using a Cumulative Sum Analysis (CUSUM) method to identify changes across time. The research question is whether and for what reason the online sentiment changed during the observation period. The sentiment expressed is triangulated with perceived real-life negative events, such as the burning of the University of KwaZulu-Natal (UKZN) library and the University of Johannesburg (UJ) Hall, to understand whether online activism sentiment reflected or reacted to real-life events. The study finds that sentiment did change in relation to these two events, one on the day of the UKZN library event and one prior to the UJ Hall event. Social robots (bots) are automatic or semi-automatic computer programs that mimic human behaviour in online social networks. Their deployment exposes online activism to manipulation. A further research question addressed whether bots played a role in the #FeesMustFall campaign. A review of bots, their characteristics, behaviour, and detection methods was undertaken. The study does indeed establish the presence of bots during #FeesMustFall. The study’s contribution is significant as this is the first longitudinal study of the #FeesMustFall campaign which observes the sentiment distribution and changes. It is also the first study to investigate and find evidence of bots in the #FeesMustFall campaign.