Identifying and Categorizing Disaster-Related Tweets

  title={Identifying and Categorizing Disaster-Related Tweets},
  author={Kevin Stowe and Michael J. Paul and Martha Palmer and Leysia Palen and Kenneth Mark Anderson},
This paper presents a system for classifying disaster-related tweets. The focus is on Twitter data generated before, during, and after Hurricane Sandy, which impacted New York in the fall of 2012. We propose an annotation schema for identifying relevant tweets as well as the more fine-grained categories they represent, and develop feature-rich classifiers for relevance and fine-grained categorization. 

Figures and Tables from this paper

Comparing Learning-Based Methods for Identifying Disaster-Related Tweets

This paper provides a system for labeling Twitter data and classifying disaster-related tweets, and applies various machine learning models on the labeled data and provides a performance comparison between the models using features generated from TfidfVectorizer and CountVectorizer Approaches.

Using social media for classifying actionable insights in disaster scenario

This work defines multiple feature sets and uses them with various supervised classification algorithms from literature to study the effectiveness of the approach in annotating the tweets with their appropriate information categories.

Analysis of Detection Models for Disaster-Related Tweets

The Disaster Tweet Corpus 2020 is introduced, an extended compilation of existing resources which comprises a total of 123,166 tweets from 46 disasters covering 9 disaster types, and the average misclassification rate of 3,8% on performance-optimized detection models indicates effective classification knowledge but comes at the price of insufficient generalizability.

Improving Classification of Twitter Behavior During Hurricane Events

It is shown that feature-based and deep learning methods provide different benefits for tweet classification, and ensemble-based methods using linguistic, temporal, and geospatial features can effectively classify user behavior during hazard events.

Applying Modified TF-IDF with Collocation in Classifying Disaster-Related Tweets

  • Gleen A. Dalaorao
  • Computer Science
    International Journal of Advanced Trends in Computer Science and Engineering
  • 2020
A combination of terms known as collocation is introduced as an improvement to TF-IDF to boost the text classification effectiveness and establishes that RandomForest consistently outperforms that two other compared classifiers.

Monitoring Social Media to Identify Environmental Crimes through NLP. A preliminary study

This paper presents the results of research carried out on the UNIOR Eye corpus, a corpus which has been built by downloading tweets related to environmental crimes, to build a model able to detect which class a tweet belongs to.

I-AID: Identifying Actionable Information From Disaster-Related Tweets

This paper proposes a system, dubbed I-AID, to automatically filter tweets with critical or actionable information from the enormous volume of social media data, and combines state-of-the-art approaches to process and represents textual data in order to capture its underlying semantics.

A deep learning-based social media text analysis framework for disaster resource management

A novel prototype system that analyzes the emergency-related tweets to classify them as need or available tweets, and a novel two-word sliding window approach is proposed to generate the combine embedding of two adjacent words.

A Sentiment-Aware Contextual Model for Real-Time Disaster Prediction Using Twitter Data

A sentiment-aware contextual model named SentiBERT-BiLSTM-CNN for disaster detection using Tweets demonstrates superior performance in the F1 score, making it a competitive model in Tweets-based disaster prediction.

Calling for Response: Automatically Distinguishing Situation-Aware Tweets During Crises

A convolutional neural network based model to automatically detect crisis-related tweets by exploring the twitter-specific linguistic, sentimental and emotional analysis along with statistical topic modeling to identify a set of quality features.



Twitter Sentiment Analysis: The Good the Bad and the OMG!

This paper evaluates the usefulness of existing lexical resources as well as features that capture information about the informal and creative language used in microblogging, and uses existing hashtags in the Twitter data for building training data.

Short text classification in twitter to improve information filtering

A small set of domain-specific features extracted from the author's profile and text is proposed to use to classify short text messages to a predefined set of generic classes such as News, Events, Opinions, Deals, and Private Messages.

Microblogging during two natural hazards events: what twitter may contribute to situational awareness

Analysis of microblog posts generated during two recent, concurrent emergency events in North America via Twitter, a popular microblogging service, aims to inform next steps for extracting useful, relevant information during emergencies using information extraction (IE) techniques.

Using Social Media to Enhance Emergency Situation Awareness

The described system uses natural language processing and data mining techniques to extract situation awareness information from Twitter messages generated during various disasters and crises.

Separating Fact from Fear: Tracking Flu Infections on Twitter

Improvements on influenza surveillance using Twitter are demonstrated by discriminating flu tweets that report infection with those that express concerned awareness of the flu, as well as tweets about the authors versus about others.

An analysis of Twitter messages in the 2011 Tohoku Earthquake

It is suggested that Twitter data can be used as a useful resource for tracking the public mood of populations affected by natural disasters as well as an early warning system.

Twitter Catches The Flu: Detecting Influenza Epidemics using Twitter

It is described that Twitter texts reflect the real world, and that NLP techniques can be applied to extract only tweets that contain useful information.

Natural Language Processing to the Rescue? Extracting "Situational Awareness" Tweets During Mass Emergency

An approach for automatically identifying messages communicated via Twitter that contribute to situational awareness that has the potential to aid the general public in culling and analyzing information communicated during times of mass emergency is described.

Think Local, Retweet Global: Retweeting by the Geographically-Vulnerable during Hurricane Sandy

It is found that the people in the path of the disaster favor in their retweeting locally-created tweets and those with locally-actionable information, and form denser networks of information propagation during disaster than before or after.

Processing Social Media Messages in Mass Emergency

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.