This study examines language and communication students’ self-perceived mastery of AI chatbot prompt engineering, with particular attention to “vibe coding” for educational mobile application development. In this study, vibe coding refers to the deliberate use of prompts to shape tone, style, audience orientation, and user-facing educational content. Using a pattern-based framework centred on roles, constraints, and examples, the study investigates how students combine structure and exploratory prompting. A quantitative cross-sectional survey was administered online during March–July 2025 (Semester 2). Complete responses from 120 undergraduates were analysed from approximately 126 invited students (analytic response rate = 95.2%). The questionnaire demonstrated excellent overall internal consistency (Cronbach’s ? = .965). Results indicate that students usually begin tasks with structured prompts but later move towards mixed or unstructured prompting styles, suggesting a control-then-explore sequence. Longer exposure to AI chatbots and more extensive prompt-engineering training were associated with higher self-perceived competency and output efficiency, whereas weekly usage frequency did not show statistically significant differences. Educational background was associated with prompting style and usage, but not with overall perceived competency or output efficiency, and gender differences were negligible. The findings suggest that scaffolded instruction in prompt engineering can support more confident and consistent student use of AI chatbots. Future research should triangulate self-reports with behavioural logs, archived prompts, and performance-based outputs.
Nur Izzati Khairuddin, M. Rashid, Hairul Azhar Mohamad et al.· International Journal of Lea...· 0 citations
This study examines the sentiment expressed in TikTok comments under the hashtag #SaveGaza to explore the emotional dynamics and key themes within this digital public. TikTok’s unique short-video format and predominantly young user base provide a distinctive environment for political and humanitarian discourse. Sentiment analysis, which classifies text into positive, negative, or neutral categories, was applied to a 100 sampled dataset of highly engaged comments on #SaveGaza posts. The analysis revealed that negative sentiment dominated, reflecting widespread anger, grief, and frustration related to the Gaza crisis. Positive sentiment was also significant, expressing solidarity, hope, and calls for peace, while neutral comments provided factual context and historical information. Key themes identified include activism, media criticism, personal storytelling, and human rights advocacy. These findings align with the concept of affective publics, where shared emotional expression on digital platforms fosters politically engaged communities. The study highlights the challenges of sentiment analysis on TikTok due to informal language, slang, emojis, and evolving online vernacular, suggesting the need for hybrid approaches combining automated tools with manual interpretation. Overall, this research contributes to understanding how sentiment analysis can be adapted to TikTok’s environment and underscores the platform’s role as a space for effective political engagement. The insights have practical implications for activists, policymakers, and scholars interested in digital public discourse on emerging social media platforms.
Hairul Azhar Mohamad, M. Rashid, Muhammad Luthfi Mohaini et al.· International journal of res...· 0 citations
The English Placement Test (EPT) allows first-semester diploma students at Universiti Teknologi MARA (UiTM) to be exempted from the compulsory first-level English proficiency course if they sit and pass it. Communicating accurate and timely information about the test across the university's branch campuses has long been difficult, because there has been no single, centralised information hub, and important materials were often lost among the many messages exchanged between lecturers and students. This study introduces AskEPTbot, a machine-learning Telegram chatbot developed to act as a one-stop centre for EPT information that is accessible to both lecturers and students. Building the chatbot involved integrating EPT information into its knowledge database and enabling a machine-learning feature designed to return increasingly accurate responses as more users interact with it. The aim was to coordinate the EPT communication system and to ease the workload of the lecturers in charge (LICs) at 22 UiTM branches nationwide, who had previously answered hundreds of enquiries individually or through WhatsApp groups. A two-pronged quantitative design combined secondary data analysis of user analytics with a user satisfaction survey. Analytics from 5,067 users showed a high volume of repeat sessions and interactions per user, and the chatbot returned accurate responses in 94.61% of the sampled cases during a single evaluation week. Survey respondents also reported high satisfaction with the chatbot's usefulness, its ability to meet expectations, its response speed, the clarity of its replies, and its ease of use. AskEPTbot therefore functioned as a practical, well-used information hub and was designed to reduce the administrative burden on LICs.
M. Rashid, Hairul Azhar Mohamad, Amir Lukman Abd Rahman et al.· International journal of res...· 0 citations