Analysis of Twitter user's location behaviors
Contents
What's the team
What’s the data you’ll work with?
We will work with a set of 500 Twitter users and all their friends. Two users are defined as friends if they follow each other. The set of core users are chosen to be those who have sent out at least N tweets with location information during the past P days.
<bliu1>
We first select a list of users in twitter who utilize location information in their tweets.
- Seed user set (SUS): we randomly select a set of users (say 500) that attach location information in their tweets. (By listening to the streaming API).
In order to make their location interpretable by us, we enforce them to be in Great Pittsburgh area.
- Extended user set (CUS) : we extract all the mutual followers of users in SUS in order to observe the social sphere of the seed users.
(if user A is in SUS, A follows B and B follows A, then B is in the EUS. B does not have to be using location feature)
Then we crawl user profiles and tweeting history for all the users in EUS in a specified time period (say 30 days) using REST API, in order to study the nature of their tweeting behavior using location.
</bliu1>
What’s the task or tasks?
Through our analysis, we would like to answer the following research questions:
- If one user sends out his/her location information actively, what can we infer about his/her friends' location behavior?
- What is most "active location user"'s motivation for posting their location information?
- What can we infer from a user's most frequent location?
- ...
How will you evaluate? (qualitative or quantitatively?)
- ?
What are the key technical challenges, and what do you hope to learn?
- It's probably gonna take some time to figure out how to get the 500 "active location users"
Related papers
- ?
