City-level Geolocation of Tweets for Real-time Visual Analytics

Real-time tweets can provide useful information on evolving events and situations. Geotagged tweets are especially useful, as they indicate the location of origin and provide geographic context. However, only a small portion of tweets are geotagged, limiting their use for situational awareness. In this paper, we adapt, improve, and evaluate a state-of-the-art deep learning model for city-level geolocation prediction, and integrate it with a visual analytics system tailored for real-time situational awareness. We provide computational evaluations to demonstrate the superiority and utility of our geolocation prediction model within an interactive system.

[1]  Duc Minh Nguyen,et al.  Multiview Deep Learning for Predicting Twitter Users' Location , 2017, ArXiv.

[2]  Alan M. MacEachren,et al.  GeoTxt: A scalable geoparsing system for unstructured text geolocation , 2019, Trans. GIS.

[3]  Stuart E. Middleton,et al.  Real-Time Crisis Mapping of Natural Disasters Using Social Media , 2014, IEEE Intelligent Systems.

[4]  Trevor Cohn,et al.  End-to-end Network for Twitter Geolocation Prediction and Hashing , 2017, IJCNLP.

[5]  Jie Tang,et al.  A Probabilistic Framework for Location Inference from Social Media , 2017, ArXiv.

[6]  Hua Lu,et al.  Location Inference for Non-Geotagged Tweets in User Timelines , 2019, IEEE Transactions on Knowledge and Data Engineering.

[7]  Ethan Zuckerman,et al.  CLIFF-CLAVIN : Determining Geographic Focus for News Articles [ Extended Abstract ] , 2014 .

[8]  David S. Ebert,et al.  Interactive Learning for Identifying Relevant Tweets to Support Real-time Situational Awareness , 2019, IEEE Transactions on Visualization and Computer Graphics.

[9]  Lars Schmidt-Thieme,et al.  Near Real-time Geolocation Prediction in Twitter Streams via Matrix Factorization Based Regression , 2016, CIKM.

[10]  Halit Oguztüzün,et al.  A survey on location estimation techniques for events detected in Twitter , 2017, Knowledge and Information Systems.

[11]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[12]  Abhinav Kumar,et al.  Location reference identification from tweets during emergencies: A deep learning approach , 2019, International Journal of Disaster Risk Reduction.

[13]  Prasant Mohapatra,et al.  Spatio-temporal provenance: Identifying location information from unstructured text , 2013, 2013 IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops).

[14]  Brenden Jongman,et al.  TAGGS: Grouping Tweets to Improve Global Geotagging for Disaster Response , 2017 .

[15]  Hua Lu,et al.  Location Inference for Non-Geotagged Tweets in User Timelines [Extended Abstract] , 2019, 2019 IEEE 35th International Conference on Data Engineering (ICDE).

[16]  Derek Ruths,et al.  Geolocation Prediction in Twitter Using Social Networks: A Critical Analysis and Review of Current Practice , 2015, ICWSM.

[17]  David S. Ebert,et al.  SMART : Social Media Analytics and Reporting Toolkit , 2017 .

[18]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.