Browsing by Author "Ibrahim, Samar"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Bilingual AI-Driven Chatbot for Academic Advising
    ((IJACSA) International Journal of Advanced Computer Science and Applications,, 2022) Bilquise, Ghazala; Ibrahim, Samar; Shaalan, Khaled
    Conversational technologies are revolutionizing how organizations communicate with people, thereby raising quick responses and constant availability expectations. Students often have queries about the institutional and academic policies and procedures, academic progression, activities, and more in an academic environment. In reality, the student services team and the academic advisors are overwhelmed with several queries that they cannot provide instant responses to, resulting in dissatisfaction with services. Our study leverages Artificial Intelligence and Natural Language processing technologies to build a bilingual chatbot that interacts with students in the English and Arabic languages. The conversational agent is built in Python and designed for students to support advising-related queries. We use a purpose-built domain-specific corpus consisting of the common questions advisors receive from students and their responses as the chatbots knowledge base. The chatbot engine determines the user intent by processing the input and retrieves the most appropriate response that matches the intent with an accuracy of 80% in English and 75% in Arabic. We also evaluated the chatbot interface by conducting field experiments with students to test the accuracy of the chatbot with real-time input and test the application interface.
  • No Thumbnail Available
    Item
    Investigating student acceptance of an academic advising chatbot in higher education institutions
    (Springer, 2023) Bilquise, Ghazala; Ibrahim, Samar; M. Salhieh, Sa’Ed
    The study explores factors affecting university students’ behavioural intentions in adopting an academic advising chatbot. The study focuses on functional, socio emotional, and relational factors affecting students’ acceptance of an AI-driven aca demic advising chatbot. The research is based on a conceptual model derived from several constructs of traditional technology acceptance models, TAM, UTAUT, the latest AI-driven self-service technologies models, the Service Robot Acceptance (sRAM) model, and the intrinsic motivation Self Determination Theory (SDT) model. The proposed conceptual model has been tailored to an educational con text. A questionnaire Survey of Non-purposive sampling technique was applied to collect data points from 207 university students from two major universities in the UAE. Subsequently, PLS-SEM causal modelling was applied for hypothesis testing. The results revealed that the functional elements, perceived ease of use and social influence significantly affect behavioural intention for chatbots’ acceptance. How ever, perceived usefulness, autonomy, and trust did not show significant evidence of influence on the acceptance of an advising chatbot. The study reviews chatbot literature and presents recommendations for educational institutions to implement AI-driven chatbots effectively for academic advising. It is one of the first studies that assesses and examines factors that impact the willingness of higher education students to accept AI-driven academic advising chatbots. This study presents sev eral theoretical contributions and practical implications for successful deployment of service-oriented chatbots for academic advising in the educational sector.