Abstract
We propose an end-to-end neural network to predict the geolocation of a tweet. The network takes as input a number of raw Twitter metadata such as the tweet message and associated user account information. Our model is language independent, and despite minimal feature engineering, it is interpretable and capable of learning location indicative words and timing patterns. Compared to state-of-the-art systems, our model outperforms them by 2%-6%. Additionally, we propose extensions to the model to compress representation learnt by the network into binary codes. Experiments show that it produces compact codes compared to benchmark hashing algorithms. An implementation of the model is released publicly.- Anthology ID:
- I17-1075
- Volume:
- Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- November
- Year:
- 2017
- Address:
- Taipei, Taiwan
- Editors:
- Greg Kondrak, Taro Watanabe
- Venue:
- IJCNLP
- SIG:
- Publisher:
- Asian Federation of Natural Language Processing
- Note:
- Pages:
- 744–753
- Language:
- URL:
- https://aclanthology.org/I17-1075
- DOI:
- Cite (ACL):
- Jey Han Lau, Lianhua Chi, Khoi-Nguyen Tran, and Trevor Cohn. 2017. End-to-end Network for Twitter Geolocation Prediction and Hashing. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 744–753, Taipei, Taiwan. Asian Federation of Natural Language Processing.
- Cite (Informal):
- End-to-end Network for Twitter Geolocation Prediction and Hashing (Lau et al., IJCNLP 2017)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/I17-1075.pdf
- Code
- jhlau/twitter-deepgeo