2021/08/04 by Oliver Karras, Karras, Oliver, Eklekta Kristo +3
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Open Source Software Innovations #Software Engineering (cs.SE) #Software Engineering Research #Software Engineering Techniques and Practices
paper · pdf · doi:10.48550/arxiv.2108.02076
openalex publication_date 2021/08/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Vision videos are established for soliciting feedback and stimulating\ndiscussions in requirements engineering (RE) practices, such as focus groups.\nDifferent researchers motivated the transfer of these benefits into crowd-based\nRE (CrowdRE) by using vision videos on social media platforms. So far, however,\nlittle research explored the potential of using vision videos for CrowdRE in\ndetail. In this paper, we analyze and assess this potential, in particular,\nfocusing on video comments as a source of feedback. In a case study, we\nanalyzed 4505 comments on a vision video from YouTube. We found that the video\nsolicited 2770 comments from 2660 viewers in four days. This is more than 50%\nof all comments the video received in four years. Even though only a certain\nfraction of these comments are relevant to RE, the relevant comments address\ntypical intentions and topics of user feedback, such as feature request or\nproblem report. Besides the typical user feedback categories, we found more\nthan 300 comments that address the topic safety, which has not appeared in\nprevious analyses of user feedback. In an automated analysis, we compared the\nperformance of three machine learning algorithms on classifying the video\ncomments. Despite certain differences, the algorithms classified the video\ncomments well. Based on these findings, we conclude that the use of vision\nvideos for CrowdRE has a large potential. Despite the preliminary nature of the\ncase study, we are optimistic that vision videos can motivate stakeholders to\nactively participate in a crowd and solicit numerous of video comments as a\nvaluable source of feedback.\n