Home Location Leakage via Weather-Related Social Media Posts
by Akitaka Yamashita, Keishi Tajima
Abstract
We analyze the extent of home location leakage via social media posts
about current local weather. To quantify this risk, we develop a
two-step location estimation method: (1) identifying user posts
mentioning current local rain or snow, and (2) ranking locations by
matching post timestamps against nationwide precipitation data. To
train a post classifier for Step (1), we collect posts including the
words ``rain'' or ``snow'' from users with known locations, and label
them as follows: if there was no precipitation there, the post is not
about the current weather; otherwise, it may or may not be about the
current weather. We then train the classifier using a variant of
Positive-Unlabeled learning. For Step (2), we design a probabilistic
model of posting behavior to rank locations based on likelihood. Our
experiment on X data demonstrates a non-negligible privacy
vulnerability: our method successfully identified the home locations
of 68\% of users with 20 posts about the current rain or snow.
Keywords
social network analysis;
user profiling;
geographic information
Published in Proc. of ACM Conference on Web Science, 6 pages, Braunschweig, Germany, 2026
/ Fax: +81(Japan) 75-753-5978 / Office: Research Bldg. #7, room 404