Graph based semi-supervised learning with convolution neural networks to classify crisis related tweets

Firoj Alam, Shafiq Rayhan Joty, Muhammad Imran

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

During time-critical situations such as natural disasters, rapid classification of data posted on social networks by affected people is useful for humanitarian organizations to gain situational awareness and to plan response efforts. However, the scarcity of labeled data in the early hours of a crisis hinders machine learning tasks thus delays crisis response. In this work, we propose to use an inductive semi-supervised technique to utilize unlabeled data, which is often abundant at the onset of a crisis event, along with fewer labeled data. Specifically, we adopt a graph-based deep learning framework to learn an inductive semi-supervised model. We use two real-world crisis datasets from Twitter to evaluate the proposed approach. Our results show significant improvements using unlabeled data as compared to only using labeled data.

Original languageEnglish
Title of host publication12th International AAAI Conference on Web and Social Media, ICWSM 2018
PublisherAAAI press
Pages556-559
Number of pages4
ISBN (Electronic)9781577357988
Publication statusPublished - 1 Jan 2018
Event12th International AAAI Conference on Web and Social Media, ICWSM 2018 - Palo Alto, United States
Duration: 25 Jun 201828 Jun 2018

Other

Other12th International AAAI Conference on Web and Social Media, ICWSM 2018
CountryUnited States
CityPalo Alto
Period25/6/1828/6/18

Fingerprint

Supervised learning
Convolution
Disasters
Learning systems
Neural networks
Deep learning

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Alam, F., Rayhan Joty, S., & Imran, M. (2018). Graph based semi-supervised learning with convolution neural networks to classify crisis related tweets. In 12th International AAAI Conference on Web and Social Media, ICWSM 2018 (pp. 556-559). AAAI press.

Graph based semi-supervised learning with convolution neural networks to classify crisis related tweets. / Alam, Firoj; Rayhan Joty, Shafiq; Imran, Muhammad.

12th International AAAI Conference on Web and Social Media, ICWSM 2018. AAAI press, 2018. p. 556-559.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Alam, F, Rayhan Joty, S & Imran, M 2018, Graph based semi-supervised learning with convolution neural networks to classify crisis related tweets. in 12th International AAAI Conference on Web and Social Media, ICWSM 2018. AAAI press, pp. 556-559, 12th International AAAI Conference on Web and Social Media, ICWSM 2018, Palo Alto, United States, 25/6/18.
Alam F, Rayhan Joty S, Imran M. Graph based semi-supervised learning with convolution neural networks to classify crisis related tweets. In 12th International AAAI Conference on Web and Social Media, ICWSM 2018. AAAI press. 2018. p. 556-559
Alam, Firoj ; Rayhan Joty, Shafiq ; Imran, Muhammad. / Graph based semi-supervised learning with convolution neural networks to classify crisis related tweets. 12th International AAAI Conference on Web and Social Media, ICWSM 2018. AAAI press, 2018. pp. 556-559
@inproceedings{79775e30c17e48e7b24df67d17b1a74b,
title = "Graph based semi-supervised learning with convolution neural networks to classify crisis related tweets",
abstract = "During time-critical situations such as natural disasters, rapid classification of data posted on social networks by affected people is useful for humanitarian organizations to gain situational awareness and to plan response efforts. However, the scarcity of labeled data in the early hours of a crisis hinders machine learning tasks thus delays crisis response. In this work, we propose to use an inductive semi-supervised technique to utilize unlabeled data, which is often abundant at the onset of a crisis event, along with fewer labeled data. Specifically, we adopt a graph-based deep learning framework to learn an inductive semi-supervised model. We use two real-world crisis datasets from Twitter to evaluate the proposed approach. Our results show significant improvements using unlabeled data as compared to only using labeled data.",
author = "Firoj Alam and {Rayhan Joty}, Shafiq and Muhammad Imran",
year = "2018",
month = "1",
day = "1",
language = "English",
pages = "556--559",
booktitle = "12th International AAAI Conference on Web and Social Media, ICWSM 2018",
publisher = "AAAI press",

}

TY - GEN

T1 - Graph based semi-supervised learning with convolution neural networks to classify crisis related tweets

AU - Alam, Firoj

AU - Rayhan Joty, Shafiq

AU - Imran, Muhammad

PY - 2018/1/1

Y1 - 2018/1/1

N2 - During time-critical situations such as natural disasters, rapid classification of data posted on social networks by affected people is useful for humanitarian organizations to gain situational awareness and to plan response efforts. However, the scarcity of labeled data in the early hours of a crisis hinders machine learning tasks thus delays crisis response. In this work, we propose to use an inductive semi-supervised technique to utilize unlabeled data, which is often abundant at the onset of a crisis event, along with fewer labeled data. Specifically, we adopt a graph-based deep learning framework to learn an inductive semi-supervised model. We use two real-world crisis datasets from Twitter to evaluate the proposed approach. Our results show significant improvements using unlabeled data as compared to only using labeled data.

AB - During time-critical situations such as natural disasters, rapid classification of data posted on social networks by affected people is useful for humanitarian organizations to gain situational awareness and to plan response efforts. However, the scarcity of labeled data in the early hours of a crisis hinders machine learning tasks thus delays crisis response. In this work, we propose to use an inductive semi-supervised technique to utilize unlabeled data, which is often abundant at the onset of a crisis event, along with fewer labeled data. Specifically, we adopt a graph-based deep learning framework to learn an inductive semi-supervised model. We use two real-world crisis datasets from Twitter to evaluate the proposed approach. Our results show significant improvements using unlabeled data as compared to only using labeled data.

UR - http://www.scopus.com/inward/record.url?scp=85050623767&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050623767&partnerID=8YFLogxK

M3 - Conference contribution

SP - 556

EP - 559

BT - 12th International AAAI Conference on Web and Social Media, ICWSM 2018

PB - AAAI press

ER -