Cluster and Sentiment Analyses of YouTube Textual Feedback of Programming Language Learners to Enhance Learning in Programming

• Main Authors: Bringula, Rex, Victorino, John Noel, De Leon, Marlene, Estuar, Ma. Regina Justina E
• Format: text
• Published: Archīum Ateneo 2019
• Subjects: Learning; Programming; Sentiment analysis; Videos; YouTube; Computer Sciences
• Online Access: https://archium.ateneo.edu/discs-faculty-pubs/182; https://link.springer.com/chapter/10.1007/978-3-030-32523-7_67
• Institution: Ateneo De Manila University

This study intends to determine the clusters and sentiments of feedback of YouTube users in learning to program in Python and C++. Toward this goal, a total of 2,583 feedback on introductory video tutorials about Python and C++ were collected. It is found that the words “thanks” and “thank” were the most frequently occurring word in both YouTube videos – indicating appreciation and helpfulness of the video tutorials. The results of k-means cluster analyses further disclosed that groups of feedback are similar across the two languages, i.e., confirmation, helpfulness, gratitude, and recommendation. YouTube users expressed positive sentiments towards the tutorial videos. Implications to teaching programming and YouTube video content development are presented. Limitations of the study are also offered.