• Corpus ID: 10755832

Rapid Classification of Crisis-Related Data on Social Networks using Convolutional Neural Networks

@article{Nguyen2016RapidCO,
  title={Rapid Classification of Crisis-Related Data on Social Networks using Convolutional Neural Networks},
  author={Tien Dat Nguyen and Kamla Al-Mannai and Shafiq R. Joty and Hassan Sajjad and Muhammad Imran and Prasenjit Mitra},
  journal={ArXiv},
  year={2016},
  volume={abs/1608.03902}
}
The role of social media, in particular microblogging platforms such as Twitter, as a conduit for actionable and tactical information during disasters is increasingly acknowledged. However, time-critical analysis of big crisis data on social media streams brings challenges to machine learning techniques, especially the ones that use supervised learning. The Scarcity of labeled data, particularly in the early hours of a crisis, delays the machine learning process. The current state-of-the-art… 

Figures and Tables from this paper

Applications of Online Deep Learning for Crisis Response Using Social Media Information
TLDR
A new online algorithm based on stochastic gradient descent is proposed to train DNNs in an online fashion during disaster situations to address two types of information needs of response organizations: identifying informative tweets and classifying them into topical classes.
A stacked convolutional neural network for detecting the resource tweets during a disaster
TLDR
St stacking of Convolutional Neural Networks with traditional feature based classifiers is proposed for detecting the NAR tweets and the experimental results proved that the proposed model achieves the best accuracy compared to baseline methods.
A deep multi-modal neural network for informative Twitter content classification during emergencies
TLDR
This paper presents a multi-modal approach to identify disaster-related informative content from the Twitter streams using text and images together based on long-short-term-memory and VGG-16 networks that show significant improvement in the performance, as evident from the validation result.
Standardizing and Benchmarking Crisis-related Social Media Datasets for Humanitarian Information Processing
TLDR
This work consolidates labels of eight annotated data sources and provides 166.1k and 141.5k tweets for informativeness and humanitarian classification tasks, respectively, resulting in a larger dataset that affords the ability to train more sophisticated models.
Multi-modal Adversarial Training for Crisis-related Data Classification on Social Media
TLDR
A multi-modal adversarial training method for crisis-related tweets classification is proposed and the evaluation results clearly demonstrate the advantages of the proposed model in improving the robustness of tweet classification.
A Comparative Analysis of Machine Learning Techniques for Disaster-Related Tweet Classification
TLDR
It is evident that the deep neural network models are performing significantly well in classifying disaster-related tweets even for imbalanced datasets.
A Hybrid Domain Adaptation Approach for Identifying Crisis-Relevant Tweets
TLDR
Huge amounts of data are generated during emergency situations and critical situations; however, no decisions are made on how to handle these situations.
A Deep Learning Approach for Tweet Classification and Rescue Scheduling for Effective Disaster Management
TLDR
A deep learning model combining attention based Bi-directional Long Short-Term Memory and Convolutional Neural Network to classify the tweets and an adaptive multi-task hybrid scheduling algorithm considering resource constraints to perform an effective rescue scheduling operation considering different rescue priorities are developed.
Unsupervised and Interpretable Domain Adaptation to Rapidly Filter Tweets for Emergency Services
TLDR
It is hypothesize that unsupervised domain adaptation through multi-task learning can be a useful framework to leverage data from past crisis events for training efficient information filtering models during the sudden onset of a new crisis.
...
...

References

SHOWING 1-10 OF 34 REFERENCES
Cross-Language Domain Adaptation for Classifying Crisis-Related Short Messages
TLDR
The past labels of past events are shown to be useful when both source and target events are of the same type (e.g. both earthquakes), and cross-language domain adaptation was useful, however, when for different languages, the performance decreased.
Identifying informative messages in disaster events using Convolutional Neural Networks
TLDR
This paper presents an approach to identifying informative messages in social media streams during disaster events based on Convolutional Neural Networks and shows significant improvement in performance over models that use the “bag of words” and n-grams as features on several datasets of messages from flooding events.
Twitter as a Lifeline: Human-annotated Twitter Corpora for NLP of Crisis-related Messages
TLDR
This paper presents human-annotated Twitter corpora collected during 19 different crises that took place between 2013 and 2015, and publishes first largest word2vec word embeddings trained on 52 million crisis-related tweets.
Bridging social media via distant supervision
TLDR
An approach to tweet classification based on distant supervision is studied, whereby a single-label multi-class classification task is applied to tweets linking to YouTube video classes, which provides for free a virtually unlimited number of labelled instances that can be used as training data.
AIDR: artificial intelligence for disaster response
TLDR
AIDR has been successfully tested to classify informative vs. non-informative tweets posted during the 2013 Pakistan Earthquake and achieved a classification quality (measured using AUC) of 80%.
Tweet4act: Using incident-specific profiles for classifying crisis-related messages
We present Tweet4act, a system to detect and classify crisis-related messages communicated over a microblogging platform. Our system relies on extracting content features from each message. These
Summarizing Situational Tweets in Crisis Scenario
TLDR
A novel framework which first assigns tweets into different situational classes and then summarize those tweets, which is time and memory efficient and outperforms the baseline in terms of quality, coverage of events, locations et al., effectiveness, and utility in disaster scenarios.
Real-time disease surveillance using Twitter data: demonstration on flu and cancer
TLDR
A novel real-time flu and cancer surveillance system that uses spatial, temporal, and text mining on Twitter data to help facilitate faster response to and preparation for epidemics and also be very useful for both patients and doctors to make more informed decisions is described.
Processing Social Media Messages in Mass Emergency
TLDR
This survey surveys the state of the art regarding computational methods to process social media messages and highlights both their contributions and shortcomings, and methodically examines a series of key subproblems ranging from the detection of events to the creation of actionable and useful summaries.
Earthquake shakes Twitter users: real-time event detection by social sensors
TLDR
This paper investigates the real-time interaction of events such as earthquakes in Twitter and proposes an algorithm to monitor tweets and to detect a target event and produces a probabilistic spatiotemporal model for the target event that can find the center and the trajectory of the event location.
...
...