Evaluation of Leveraging Natural Language Insight for Customer Sentiment Analysis at JOBJACK SME

Nelisiwe Sibisi and Sam Lubbe
Additional contact information
Nelisiwe Sibisi: Stadio Higher Education, Krugersdorp, South Africa
Sam Lubbe: Stadio Higher Education, Krugersdorp, South Africa

Technium Social Sciences Journal, 2026, vol. 80, issue 1, 199-210

Abstract: As digital platforms increasingly serve as vital intermediaries in the South African labor market, they offer a promising avenue for addressing the systemic challenge of high youth unemployment. Platforms like JOBJACK facilitate connections between entry-level seekers and employers; however, the rapid scaling of these services has generated an overwhelming volume of unstructured data. Small and Medium Enterprises (SMEs) in this sector often find themselves data-rich but insight-poor, struggling to systematically process diverse feedback streams—including application comments, helpdesk queries, and social media interactions—into actionable business intelligence. While traditional quantitative metrics provide high-level snapshots of platform activity, they consistently fail to capture the nuanced underlying user sentiments, such as frustration with technical barriers or developing trust in the digital ecosystem. This study explores the critical gap between raw data collection and strategic service improvement. By examining the limitations of current analytical frameworks used by South African SMEs, the research underscores the necessity of integrating advanced qualitative sentiment analysis into operational workflows. Ultimately, the paper argues that for digital labour platforms to maintain user retention and drive socio-economic impact, they must transition toward sophisticated data processing models that prioritize the human experience embedded within unstructured user feedback.

Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://techniumscience.com/index.php/socialsciences/article/view/13439 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:tec:journl:ojs:13439

DOI: 10.47577/tssj.v80i1.13439

Access Statistics for this article

Technium Social Sciences Journal is currently edited by Tasente Tanase

More articles in Technium Social Sciences Journal from Technium Science
Bibliographic data for series maintained by Tasente Tanase ( this e-mail address is bad, please contact ).