Exploiting Text and Network Context for Geolocation of Social Media Users
0 likes354 views
This document presents methods for geolocating social media users based on text and network information from Twitter data. It compares text-based, network-based, and hybrid models. The text-based model uses logistic regression on text features, the network-based model uses label propagation on the mention network, and the hybrid model initializes label propagation with text predictions. Evaluation on three Twitter datasets shows the hybrid method achieves state-of-the-art results, utilizing both text and network information.
Exploiting Text and Network Context for Geolocation of Social Media Users
- 1. Exploiting Text and Network Context for Geolocation of Social Media Users Afshin Rahimi,♥ Duy Vu,♠ Trevor Cohn,♥ and Timothy Baldwin♥ ♥ Department of Computing and Information Systems, ♠ Department of Mathematics and Statistics, The University of Melbourne OVERVIEW Task: Find the location of Twitter users based on text and net- work information Previous Shortcoming: No comparison of text-based and network-based models, no use of both. Datasets: 3 Twitter geolocation datasets: GeoText, Twitter-US, Twitter-World. Sample Format: userid, text, mention-list, latitude/longitude YOU ARE WHERE YOUR WORDS SAY YOU ARE Usage of mountain in U.S. TEXT-BASED MODEL (LR) Logistic regression with l1 regularisation over k-d tree discretisation of latitude/longitude. 130 120 110 100 90 80 70 60 Longitude 25 30 35 40 45 50 Latitude YOU ARE WHERE YOUR FRIENDS ARE Most of our online interactions are local. Twitter mention NETWORK-BASED MODEL (LP) Label Propagation in @-mention Network: • Build an @-mention network. • Initialise the location of training nodes with their known location. • Iteratively update non-training nodes’ location to the median of their neighbours. • Converges after 10 iterations. NETWORK VERSUS TEXT • For connected users, Network-based models are more accurate. • For disconnected users (about 20% of the nodes), Text-based models are more accurate. • Solution: Utilise both text and network informa- tion together! LABEL PROPAGATION OVER TEXT PREDICTIONS • Initialise training nodes with their known location and test nodes with their text-based prediction. • Iteratively update the location of non-training nodes to the median of their neighbours. • Converges after 10 iterations. • Isolated test nodes will keep their text-based prediction. DENVER’S TOP FEATURES RESULTS State of the art results over all three datasets! GEOTEXT TwitterUS TwitterWorld0 100 200 300 400 500 600 MedianErrorinkm Text-based Method (LR) Network-based Method (LP) Hybrid Method (LP-LR) Wing and Baldrige (2014) Ahmed et al. (2013)