Claim Missing Document
Check
Articles

Found 2 Documents
Search

Examining 1D and 2D CNN Architectures in Comparison for Sentiment Analysis in Sequential Data: A Case Study of Spotify Music Reviews Matobobo, Courage; Garidzira, Tinashe Crispen
The Indonesian Journal of Computer Science Vol. 14 No. 2 (2025): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i2.4740

Abstract

This study examines the comparative performance of one-dimensional (1D) and two-dimensional (2D) Convolutional Neural Networks (CNNs) in processing sequential data for sentiment analysis, using Spotify music reviews as a case study. Leveraging a custom dataset from Kaggle, the study examines the effectiveness of CNN architectures in extracting meaningful patterns from text input. The study integrates PyTorch and TorchText for efficient data preprocessing and model deployment. Both architectures are evaluated based on classification accuracy, computational efficiency, and ability to handle sequential dependencies. The results highlight the strengths and limitations of each method, providing insight into their suitability for similar tasks in text-based sentiment analysis. This research provides valuable guidance for researchers and practitioners working on sequential data tasks, emphasizing the role of architectural design in achieving optimal performance.
Exploring the Impact of Gender on Student Access to and Utilization of Educational Technology in South African Higher Education: A Systematic Review on Equity and Inclusion Matobobo, Ophellia; Matobobo, Courage
COMPETITIVE: Journal of Education Vol. 4 No. 4 (2025): Transformative Education and Learning
Publisher : Perkumpulan Dosen Fakultas Agama Islam Indramayu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58355/competitive.v4i4.199

Abstract

This study explored the impact of gender on student access to and utilization of educational technologies in South African higher education, with a focus on how these dynamics affect equity and inclusion. Using a systematic review approach, sixteen peer-reviewed studies were analysed thematically to uncover patterns of gendered disparities across technological platforms, learning contexts, and student demographics. The findings reveal that female students, particularly those from rural, low-income, or marginalised backgrounds, face significant structural barriers to accessing devices, connectivity, and digital learning spaces. Gendered social roles and responsibilities also shape how technology is used, with women often engaging more passively and asynchronously due to caregiving duties and domestic constraints, while men dominate synchronous and institutional platforms. Intersectional disadvantages, especially among incarcerated women and those with disabilities, further compound digital exclusion. Although female students frequently demonstrate strong academic outcomes when provided equitable access, institutional policies and support systems remain inadequately gender-responsive. The study concludes that meaningful inclusion in digital higher education requires not only access but also the freedom and institutional support to engage equitably. The paper calls for gender-sensitive policy reform, inclusive EdTech design, and targeted interventions that dismantle systemic barriers to digital participation in higher education.