So, Hornet is currently the most popular geo-social dating application for gay/bi men in Turkey. That is why I decided to study interactions there and my intention is to draw my sample for the quantitative part of the research from discreet Hornet users. Problem is those users are discreet meaning that they either have no picture on their profile (they don't see them unless they contact you), or they have pictures of part of their bodies, or random pics on their profile. Some of them identify their discreet status with hashtags. Anyways, I assume that maybe there are 1000-2000 Online hornet users on average at any time in a day in Turkey.
What should be the sample size for the survey, quantitative part?
How would you go about contacting those discreet members of the application?
Would you perhaps create a researcher account explicitly stating that you look for Discreet users?
Or, how about individually contacting people on the platform? Would it be representative and/or ethical?
i have no field experience in social sciences, especially quantitative research. So I wonder how would you go about collecting this data?
Meric -
Maybe there is something in the paper linked below, or in the references to that paper, that might help you. I am not familiar with the content that might most likely pertain to your project, but I believe the author to be very competent:
"Beyond traditional survey taking: adapting to a changing world
Explorations in Non-Probability Sampling Using the Web"
Proceedings of Statistics Canada Symposium 2014
J. Michael Brick
http://www.statcan.gc.ca/sites/default/files/media/14252-eng.pdf
Some of the references are likely available on ResearchGate. Like this one:
https://www.researchgate.net/publication/273561892_Summary_Report_of_the_AAPOR_Task_Force_on_Non-probability_Sampling?ev=prf_pub
Or other contributions under Mike Brick might help:
https://www.researchgate.net/profile/J_Brick
But again, in general, this is not my area, I'm just guessing you might find something there. Maybe.
Mike has a number of papers on ResearchGate, but he does not appear to participate in q&a. I think he is rather busy, so I suggest you just look at his papers.
Cheers - Jim
Article Summary Report of the AAPOR Task Force on Non-probability Sampling
Hello Meriç,
I've used Grindr before for data collection. We created a researcher account and put a picture of the university logo as the user picture. We had some success this way using two recruitment strategies:
1. Paid advertisement - for approximately AUD$500 we had an adverstisment appear upon log-in to Grindr users in the area for a 24 hour period. We had 300 respondents.Of course, this relies on you having a budget.
2. Using the account, we formulated a script and contact nearby people who were online, with individual invitations to participate in the research.
My colleague Yasin Koc (Now at University of Sussex) has used Grindr for data collection in Turkey (Istanbul), for a qualitative (interview) study, with some published success:
Eslen-Ziya, H., & Koc, Y. (2016). Being a gay man in Turkey: internalised sexual prejudice as a function of prevalent hegemonic masculinity perceptions. Culture, health & sexuality, 1-13.
Good luck!
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size