Deep Learning-Based Spatial Analytics for Disaster-Related Tweets: An Experimental Study

Online social networks are being widely used during unexpected large-scale disasters not only for sharing latest news but also requesting emergency rescues. Particularly, social network posts with their location information are becoming more important because they can be utilized for emergency management, urban planning, and various studies to understand effects of the disasters. Despite their importance, the percentage of such posts is generally tiny. In this paper, to address the location sparsity problem on Twitter in the event of disasters, we propose a deep learning-based framework to spatially analyze the disaster-related tweets by focusing on classifying tweets from affected areas of disasters. We also study effects of different deep learning architectures and input embedding techniques for this classification task. Our experimental results demonstrate that our ConvNet model with the Word2vec word embedding has the highest classification accuracy.

[1]  Hiroyuki Kitagawa,et al.  Online User Location Inference Exploiting Spatiotemporal Correlations in Social Streams , 2014, CIKM.

[2]  Jian Zhang,et al.  A Distributed Semi-Supervised Platform for DNase-Seq Data Analytics using Deep Generative Convolutional Networks , 2018, BCB.

[3]  Mudhakar Srivatsa,et al.  When twitter meets foursquare: tweet location prediction using foursquare , 2014, MobiQuitous.

[4]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[5]  Toon Calders,et al.  Predicting Visitors Using Location-Based Social Networks , 2018, 2018 19th IEEE International Conference on Mobile Data Management (MDM).

[6]  Aixin Sun,et al.  A Survey of Location Prediction on Twitter , 2017, IEEE Transactions on Knowledge and Data Engineering.

[7]  Sue Moon,et al.  Inferring Twitter user locations with 10 km accuracy , 2014, WWW.

[8]  Zhong Zhou,et al.  Tweet2Vec: Character-Based Distributed Representations for Social Media , 2016, ACL.

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

[10]  Jason Baldridge,et al.  Hierarchical Discriminative Classification for Text-Based Geolocation , 2014, EMNLP.

[11]  Xiang Li,et al.  Next Check-in Location Prediction via Footprints and Friendship on Location-Based Social Networks , 2018, 2018 19th IEEE International Conference on Mobile Data Management (MDM).

[12]  Tomoki Taniguchi,et al.  A Simple Scalable Neural Networks based Model for Geolocation Prediction in Twitter , 2016, NUT@COLING.

[13]  Kisung Lee,et al.  Automated Breast Cancer Diagnosis Using Deep Learning and Region of Interest Detection (BC-DROID) , 2017, BCB.

[14]  Seungwon Yang,et al.  Social and geographical disparities in Twitter use during Hurricane Harvey , 2018, Int. J. Digit. Earth.

[15]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[17]  Tao Wang,et al.  End-to-end text recognition with convolutional neural networks , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[18]  Jian Zhang,et al.  Deep Generative Breast Cancer Screening and Diagnosis , 2018, MICCAI.

[19]  Timothy Baldwin,et al.  A Neural Model for User Geolocation and Lexical Dialectology , 2017, ACL.

[20]  Gerald Penn,et al.  Convolutional Neural Networks for Speech Recognition , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[21]  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).

[22]  Sungyong Seo,et al.  CSI: A Hybrid Deep Model for Fake News Detection , 2017, CIKM.

[23]  M. de Rijke,et al.  Short Text Similarity with Word Embeddings , 2015, CIKM.

[24]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[25]  Tomoki Taniguchi,et al.  Unifying Text, Metadata, and User Network Representations with a Neural Network for Geolocation Prediction , 2017, ACL.

[26]  Timothy Baldwin,et al.  Text-Based Twitter User Geolocation Prediction , 2014, J. Artif. Intell. Res..

[27]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[28]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[29]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[30]  Seung-Jong Park,et al.  Evaluation of Deep Learning Frameworks Over Different HPC Architectures , 2017, 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS).

[31]  Seung-Jong Park,et al.  GPU-Accelerated Large-Scale Genome Assembly , 2018, 2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS).

[32]  Ming Zhou,et al.  Named entity recognition for tweets , 2013, TIST.