Identifying Emergency Stages in Facebook Posts of Police Departments with Convolutional and Recurrent Neural Networks and Support Vector Machines

Nicolai Pogrebnyakov; Edgar Maldonado

doi:10.1109/BigData.2017.8258464

Identifying Emergency Stages in Facebook Posts of Police Departments with Convolutional and Recurrent Neural Networks and Support Vector Machines

Nicolai Pogrebnyakov, Edgar Maldonado

University of Denver

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

99 Downloads (Pure)

Abstract

Classification of social media posts in emergency response is an important practical problem: accurate classification can help automate processing of such messages and help other responders and the public react to emergencies in a timely fashion. This research focused on classifying Facebook messages of US police departments. Randomly selected 5,000 messages were used to train classifiers that distinguished between four categories of messages: emergency preparedness, response and recovery, as well as general engagement messages. Features were represented with bag-of-words and word2vec, and models were constructed using support vector machines (SVMs) and convolutional (CNNs) and recurrent neural networks (RNNs). The best performing classifier was an RNN with a custom-trained word2vec model to represent features, which achieved the F1 measure of 0.839.

Original language	English
Title of host publication	Proceedings. 2017 IEEE International Conference on Big Data : IEEE Big Data 2017
Editors	Jian-Yun Nie, Zoran Obradovic, Toyotaro Suzumura, Rumi Ghosh, Raghunath Nambiar, Chonggang Wang, Hui Zang, Ricardo Baeza-Yates, Xiaohua Hu, Jeremy Kepner, Alfredo Cuzzocrea, Jian Tang, Masashi Toyoda
Number of pages	10
Place of Publication	Los Alamitos, CA
Publisher	IEEE
Publication date	2017
Pages	4343-4352
ISBN (Print)	9781538627167
ISBN (Electronic)	9781538627150, 9781538627143
DOIs	https://doi.org/10.1109/BigData.2017.8258464
Publication status	Published - 2017
Event	Fifth IEEE International Conference on Big Data. IEEE BigData 2017 - Boston, United States Duration: 11 Dec 2017 → 14 Dec 2017 Conference number: 5 http://cci.drexel.edu/bigdata/bigdata2017/

Conference

Conference	Fifth IEEE International Conference on Big Data. IEEE BigData 2017
Number	5
Country/Territory	United States
City	Boston
Period	11/12/2017 → 14/12/2017
Internet address	http://cci.drexel.edu/bigdata/bigdata2017/

Keywords

Social media
Classification
Police
Support vector machines
Neural networks

Access to Document

10.1109/BigData.2017.8258464Licence: Unspecified

https://arxiv.org/ftp/arxiv/papers/1801/1801.00801.pdfLicence: Unspecified

Handle.net

Persistent link

Cite this

Pogrebnyakov, N., & Maldonado, E. (2017). Identifying Emergency Stages in Facebook Posts of Police Departments with Convolutional and Recurrent Neural Networks and Support Vector Machines. In J.-Y. Nie, Z. Obradovic, T. Suzumura, R. Ghosh, R. Nambiar, C. Wang, H. Zang, R. Baeza-Yates, X. Hu, J. Kepner, A. Cuzzocrea, J. Tang, & M. Toyoda (Eds.), Proceedings. 2017 IEEE International Conference on Big Data: IEEE Big Data 2017 (pp. 4343-4352). IEEE. https://doi.org/10.1109/BigData.2017.8258464

Pogrebnyakov, Nicolai ; Maldonado, Edgar. / Identifying Emergency Stages in Facebook Posts of Police Departments with Convolutional and Recurrent Neural Networks and Support Vector Machines. Proceedings. 2017 IEEE International Conference on Big Data: IEEE Big Data 2017. editor / Jian-Yun Nie ; Zoran Obradovic ; Toyotaro Suzumura ; Rumi Ghosh ; Raghunath Nambiar ; Chonggang Wang ; Hui Zang ; Ricardo Baeza-Yates ; Xiaohua Hu ; Jeremy Kepner ; Alfredo Cuzzocrea ; Jian Tang ; Masashi Toyoda. Los Alamitos, CA : IEEE, 2017. pp. 4343-4352

@inproceedings{b02d47fdb20f45c1a8cfa394be75bf78,

title = "Identifying Emergency Stages in Facebook Posts of Police Departments with Convolutional and Recurrent Neural Networks and Support Vector Machines",

abstract = "Classification of social media posts in emergency response is an important practical problem: accurate classification can help automate processing of such messages and help other responders and the public react to emergencies in a timely fashion. This research focused on classifying Facebook messages of US police departments. Randomly selected 5,000 messages were used to train classifiers that distinguished between four categories of messages: emergency preparedness, response and recovery, as well as general engagement messages. Features were represented with bag-of-words and word2vec, and models were constructed using support vector machines (SVMs) and convolutional (CNNs) and recurrent neural networks (RNNs). The best performing classifier was an RNN with a custom-trained word2vec model to represent features, which achieved the F1 measure of 0.839.",

keywords = "Social media, Classification, Police, Support vector machines, Neural networks, Social media, Classification, Police, Support vector machines, Neural networks",

author = "Nicolai Pogrebnyakov and Edgar Maldonado",

year = "2017",

doi = "10.1109/BigData.2017.8258464",

language = "English",

isbn = "9781538627167",

pages = "4343--4352",

editor = "Jian-Yun Nie and Zoran Obradovic and Toyotaro Suzumura and Rumi Ghosh and Raghunath Nambiar and Chonggang Wang and Hui Zang and Ricardo Baeza-Yates and Xiaohua Hu and Jeremy Kepner and Alfredo Cuzzocrea and Jian Tang and Masashi Toyoda",

booktitle = "Proceedings. 2017 IEEE International Conference on Big Data",

publisher = "IEEE",

address = "United States",

note = "Fifth IEEE International Conference on Big Data. IEEE BigData 2017 ; Conference date: 11-12-2017 Through 14-12-2017",

url = "http://cci.drexel.edu/bigdata/bigdata2017/",

}

Pogrebnyakov, N & Maldonado, E 2017, Identifying Emergency Stages in Facebook Posts of Police Departments with Convolutional and Recurrent Neural Networks and Support Vector Machines. in J-Y Nie, Z Obradovic, T Suzumura, R Ghosh, R Nambiar, C Wang, H Zang, R Baeza-Yates, X Hu, J Kepner, A Cuzzocrea, J Tang & M Toyoda (eds), Proceedings. 2017 IEEE International Conference on Big Data: IEEE Big Data 2017. IEEE, Los Alamitos, CA, pp. 4343-4352, Fifth IEEE International Conference on Big Data. IEEE BigData 2017, Boston, Massachusetts, United States, 11/12/2017. https://doi.org/10.1109/BigData.2017.8258464

Identifying Emergency Stages in Facebook Posts of Police Departments with Convolutional and Recurrent Neural Networks and Support Vector Machines. / Pogrebnyakov, Nicolai; Maldonado, Edgar.
Proceedings. 2017 IEEE International Conference on Big Data: IEEE Big Data 2017. ed. / Jian-Yun Nie; Zoran Obradovic; Toyotaro Suzumura; Rumi Ghosh; Raghunath Nambiar; Chonggang Wang; Hui Zang; Ricardo Baeza-Yates; Xiaohua Hu; Jeremy Kepner; Alfredo Cuzzocrea; Jian Tang; Masashi Toyoda. Los Alamitos, CA: IEEE, 2017. p. 4343-4352.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Identifying Emergency Stages in Facebook Posts of Police Departments with Convolutional and Recurrent Neural Networks and Support Vector Machines

AU - Pogrebnyakov, Nicolai

AU - Maldonado, Edgar

N1 - Conference code: 5

PY - 2017

Y1 - 2017

N2 - Classification of social media posts in emergency response is an important practical problem: accurate classification can help automate processing of such messages and help other responders and the public react to emergencies in a timely fashion. This research focused on classifying Facebook messages of US police departments. Randomly selected 5,000 messages were used to train classifiers that distinguished between four categories of messages: emergency preparedness, response and recovery, as well as general engagement messages. Features were represented with bag-of-words and word2vec, and models were constructed using support vector machines (SVMs) and convolutional (CNNs) and recurrent neural networks (RNNs). The best performing classifier was an RNN with a custom-trained word2vec model to represent features, which achieved the F1 measure of 0.839.

AB - Classification of social media posts in emergency response is an important practical problem: accurate classification can help automate processing of such messages and help other responders and the public react to emergencies in a timely fashion. This research focused on classifying Facebook messages of US police departments. Randomly selected 5,000 messages were used to train classifiers that distinguished between four categories of messages: emergency preparedness, response and recovery, as well as general engagement messages. Features were represented with bag-of-words and word2vec, and models were constructed using support vector machines (SVMs) and convolutional (CNNs) and recurrent neural networks (RNNs). The best performing classifier was an RNN with a custom-trained word2vec model to represent features, which achieved the F1 measure of 0.839.

KW - Social media

KW - Classification

KW - Police

KW - Support vector machines

KW - Neural networks

KW - Social media

KW - Classification

KW - Police

KW - Support vector machines

KW - Neural networks

U2 - 10.1109/BigData.2017.8258464

DO - 10.1109/BigData.2017.8258464

M3 - Article in proceedings

SN - 9781538627167

SP - 4343

EP - 4352

BT - Proceedings. 2017 IEEE International Conference on Big Data

A2 - Nie, Jian-Yun

A2 - Obradovic, Zoran

A2 - Suzumura, Toyotaro

A2 - Ghosh, Rumi

A2 - Nambiar, Raghunath

A2 - Wang, Chonggang

A2 - Zang, Hui

A2 - Baeza-Yates, Ricardo

A2 - Hu, Xiaohua

A2 - Kepner, Jeremy

A2 - Cuzzocrea, Alfredo

A2 - Tang, Jian

A2 - Toyoda, Masashi

PB - IEEE

CY - Los Alamitos, CA

T2 - Fifth IEEE International Conference on Big Data. IEEE BigData 2017

Y2 - 11 December 2017 through 14 December 2017

ER -

Pogrebnyakov N, Maldonado E. Identifying Emergency Stages in Facebook Posts of Police Departments with Convolutional and Recurrent Neural Networks and Support Vector Machines. In Nie JY, Obradovic Z, Suzumura T, Ghosh R, Nambiar R, Wang C, Zang H, Baeza-Yates R, Hu X, Kepner J, Cuzzocrea A, Tang J, Toyoda M, editors, Proceedings. 2017 IEEE International Conference on Big Data: IEEE Big Data 2017. Los Alamitos, CA: IEEE. 2017. p. 4343-4352 doi: 10.1109/BigData.2017.8258464