Not logged in.
Quick Search - Contribution
Contribution Details
| Type | Master's Thesis |
| Scope | Discipline-based scholarship |
| Title | Understanding the population bias of Stack Overflow survey respondents |
| Organization Unit | |
| Authors |
|
| Supervisors |
|
| Language |
|
| Institution | University of Zurich |
| Faculty | Faculty of Business, Economics and Informatics |
| Date | 2020 |
| Abstract Text | Stack Overflow (SO) is recognized as a technical knowledge-sharing market where goods and services are merely based on asking questions and providing answers. The majority of the questions are related to technology and coding problems. Each year SO publishes a survey with an idea to reach out to coders across the world and to gain more insight into its users and their experience on the platform. SO does everything to serve the needs within the developers' community. The data obtained from the annual survey helps to make changes and set goals to improve the environment and make it more welcoming and inclusive of the SO community. The community does only include visitors to SO, but also everyone who codes or does some coding in their work or studies. The survey questionnaire starts with questions about user demographics, coding interests, current company experience, preferences for diff erent coding languages, and getting feedback on leading technologies of the time. To maximize the accuracy of results, the platform has a minimum threshold for total time spent by each candidate in completing the survey. The platform provides a census badge to its users after completing the survey. The badge falls under the silver badge category and exhibits high reputation scores. This study is a quantitative attempt to understand the diff erences among the users who participate in the developers' survey to the ones who do not participate. We wanted to identify the key factors that may influence participation in the survey to gain better understanding of the population that takes the survey and how they di ffer - if at all - from the rest of the community. It also aimed to help us understand the attitude of underrepresented groups such as women and non-active users towards the developers' survey. Our findings suggested that the majority of survey respondents belonged to the community of users with high reputation scores on the website. The users with high tenure on the website were also more likely to participate in the survey. The self-promoters - users who actively promote themselves on the website, and also on other social media platforms such as LinkedIn, Twitter, and Github - were among the majority of survey participants. In terms of user activity on the website, 85% of the survey participants were active answer providers. We also aggregated the participation from the level of participation of the users to the level of geographical regions and learned that the users from the continent of Oceania were the principal contributors in the survey, followed closely by those from Africa and South America; Europe came a distant fourth, and the contribution rate of users from Asia was the lowest of all. We could not find statistically signi cant results for users from North America. It is inquisitive for us see if the census badge leads to more participation. Our study suggests that in 2017, 40% of the respondents claimed the badge, followed by 50% in 2018 and 60% in 2019. The participation-to-badge-claim ratio has increased by 10% each year from 2017 to 2019. |
| PDF File |
Download
|
| Export |
BibTeX
|