arXiv subjects

George Boateng

Publications and source records attributed to George Boateng.

21 records · Page 2Linked to original sources

arXiv2021

AutoGrad: Automated Grading Software for Mobile Game Assignments in SuaCode Courses

Automatic grading systems have been in existence since the turn of the half-century. Several systems have been developed in the literature with either static analysis and dynamic analysis or a hybrid of both methodologies for computer science courses. This paper presents AutoGrad, a novel portable cross-platform automatic grading system for graphical Processing programs developed on Android smartphones during an online course. AutoGrad uses Processing, which is used in the emerging Interactive Media Arts, and pioneers grading systems utilized outside the sciences to assist tuition in the Arts. It also represents the first system built and tested in an African context across over thirty-five countries across the continent. This paper first explores the design and implementation of AutoGrad. AutoGrad employs APIs to download the assignments from the course platform, performs static and dynamic analysis on the assignment to evaluate the graphical output of the program, and returns the grade and feedback to the student. It then evaluates AutoGrad by analyzing data collected from the two online cohorts of 1000+ students of our SuaCode smartphone-based course. From the analysis and students' feedback, AutoGrad is shown to be adequate for automatic assessment, feedback provision to students, and easy integration for both cloud and standalone usage by reducing the time and effort required in grading the 4 assignments required to complete the course.

cs.HC↗

arXiv2021

SuaCode Africa: Teaching Coding Online to Africans using Smartphones

There is a burgeoning trend of smartphone ownership in Africa due to the low costs of Android smartphones and the global increase in social media usage. Building upon previous works that introduced a smartphone-based coding course to secondary and tertiary students in Ghana via an in-person program and an online course, this work introduced Africans in 37 countries to our online smartphone-based course in 2019. Students in this 8-week course read lesson notes, submitted assignments, collaborated with peers, and facilitators in an online forum and completed open and closed-ended surveys after the course. We performed qualitative and quantitative analyses on the data from the course. Out of the 709 students that applied, 210 were officially admitted to the course after passing the preliminary assignments. And at the end of the course, 72% of the 210 students completed the course. Additionally, students' assignment submissions and self-reports showed an understanding of the programming concepts, with comparable performance between males and females and across educational levels. Also, students mentioned that the lesson notes were easy to understand and they enjoyed the experience of writing code on their smartphones. Moreover, students adequately received help from peers and facilitators in the course forum. Lastly, results of a survey sent to students a year after completing this program showed that they had developed various applications, wrote online tutorials, and learned several tools and technologies. We were successful at introducing coding skills to Africans using smartphones through SuaCode Africa.

cs.HC↗

arXiv2021

Kwame: A Bilingual AI Teaching Assistant for Online SuaCode Courses

Introductory hands-on courses such as our smartphone-based coding course, SuaCode require a lot of support for students to accomplish learning goals. Online environments make it even more difficult to get assistance especially more recently because of COVID-19. Given the multilingual context of SuaCode students - learners across 42 African countries that are mostly Anglophone or Francophone - in this work, we developed a bilingual Artificial Intelligence (AI) Teaching Assistant (TA) - Kwame - that provides answers to students' coding questions from SuaCode courses in English and French. Kwame is a Sentence-BERT (SBERT)-based question-answering (QA) system that we trained and evaluated offline using question-answer pairs created from the course's quizzes, lesson notes and students' questions in past cohorts. Kwame finds the paragraph most semantically similar to the question via cosine similarity. We compared the system with TF-IDF and Universal Sentence Encoder. Our results showed that fine-tuning on the course data and returning the top 3 and 5 answers improved the accuracy results. Kwame will make it easy for students to get quick and accurate answers to questions in SuaCode courses.

cs.CL↗