Utilizing External Knowledge to Enhance Location Prediction for Twitter/X Users in Low Resource Settings
ACM Transactions on Spatial Algorithms and Systems · 30.09.2024 · 10 (3) · 1-25
DOI: 10.1145/3673899 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Spatial Algorithms and Systems, online erschienen am 13.07.2024. Verfasst von Yaguang Liu und 1 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: National Science Foundation, National Collaborative on Gun Violence Research, Massive Data Institute (MDI) at Georgetown University.
Abstract (Originalsprache)
Accurate estimates of user location are important for many online services, including event detection, disaster management, and determining public opinion. Neural network-based techniques have proven to be highly effective in predicting user location. However, these models typically require a large amount of labeled training data, which can be difficult to obtain in real-world scenarios. In this article, we present two approaches to tackle the issue of limited training data when predicting city level location. First, we consider a self-supervised approach that trains a state-level model without labeled data and then integrate this knowledge into the training dataset used for city-level predictions. Second, we explore the option of increasing the number of training examples by utilizing external resources to generate synthetic users . Finally, we combine these two strategies, exploiting the benefits of both. We empirically evaluate our proposed techniques on multiple Twitter/X datasets and show that our models perform significantly better than the state-of-the-art with improvements of up to 6% for Acc@161 and 8% for F1 score.
Förderung
- National Science Foundation
- National Collaborative on Gun Violence Research
- Massive Data Institute (MDI) at Georgetown University
Zitieren
APA
Liu, Y., & Singh, L. (2024). Utilizing External Knowledge to Enhance Location Prediction for Twitter/X Users in Low Resource Settings. ACM Transactions on Spatial Algorithms and Systems, 10(3), 1-25. https://doi.org/10.1145/3673899
Vancouver
Liu Y, Singh L. Utilizing External Knowledge to Enhance Location Prediction for Twitter/X Users in Low Resource Settings. ACM Transactions on Spatial Algorithms and Systems. 2024;10(3):1-25. doi:10.1145/3673899
BibTeX
@article{Liu2024,
author = {Liu, Yaguang and Singh, Lisa},
title = {Utilizing External Knowledge to Enhance Location Prediction for Twitter/X Users in Low Resource Settings},
journal = {ACM Transactions on Spatial Algorithms and Systems},
year = {2024},
volume = {10},
number = {3},
pages = {1--25},
doi = {10.1145/3673899}
}
EUVIMED