Analyzing User Comments on YouTube Coding Tutorial Videos

Abstract

I would like to thank my co-authors, Nishant Jha, Grant Williams, Jazmine Staten, and Miles Vesper for their assistance and contributions on this work. I also would like to acknowledge my study participants for their time. This accomplishment would have not been possible without my family and friends. I thank my family for their love and support and for being an example of hard work, inspiration, and dedication. I thank my parents Hollis and Lillian Poché for their encouragement and guidance. Words cannot describe the significance of their love. I thank my sister Caroline Schneider and her husband Chris Schneider for their help and support during my studies. I thank my sister Annie Suarez, her husband Joshua Suarez, and niece Olivia Suarez for keeping me uplifted. I thank Mike and Carol Schneider for their hospitality. Last but not least, I would like to thank my friends across the United States for helping me through the hard times and demonstrating true friendship. iii TABLE OF CONTENTS

SIEVE: Helping developers sift wheat from chaff via cross-platform analysis

“…These threats are related to the suitability of the evaluation metrics that we use for analyzing the result. We use the same evaluation metrics used to evaluate previous studies [52,42] to enable fair comparisons (i.e., Accuracy@k, Precision, Recall and F-measure). Therefore, we believe that the threat to construct validity is minimal.…”

“…Tools to help developers find relevant content from software engineering videos have been proposed in [45,75]. Poché et al analyzed user comments related to software engineering videos posted on YouTube [42] and proposed a technique for finding relevant comments.…”

“…Developers as content creators will also be able to digest feedback from valuable comments given by their viewers. It will help content creators to improve their future videos [42].…”

“…We then leverage the word embeddings vectors to solve information retrieval and classification problems in two different target platforms. We experiment with two different use cases: finding tweets relevant to software development on Twitter [52], and classifying useful comments for software engineering video tutorials on YouTube [42]. We conducted experiments based on the existing golden datasets provided by Sharma et al [52] for Twitter, and Poché et al [42] for YouTube comments.…”

Should Explanations of Program Code Use Audio, Text, or Both? A Replication Study

“…Others have asked learners to create programming videos for peer instruction [25] or crowdsourced video-like program animations from learners [32]. For better or worse, many online courses have students spend a lot of their study time watching video lectures (e.g., [12]), while in informal learning, many learners have embraced video-based activities such as watching experts program either live or after-the-fact [33,73]. Tools are being developed to enhance learning from programming videos and live streams and to assist in their creation [17,46,52].…”