Witness Identification in Twitter

  title={Witness Identification in Twitter},
  author={Rui Fang and Armineh Nourbakhsh and Xiaomo Liu and Sameena Shah and Quanzhi Li},
Identifying witness accounts is important for rumor debunking, crises management, and basically any task that involves on the ground eyes. The prevalence of social media has provided citizen journalism with scale and eye witnesses prominence. However, the amount of noise on social media also makes it likely that witness accounts get buried too deep in the noise and are never discovered. In this paper, we explore automatic witness identification in Twitter during emergency events. We attempt to… 

Figures and Tables from this paper

Real-World Witness Detection in Social Media via Hybrid Crowdsensing

This work develops a witness detection system based on a machine learning classifier using a wide set of linguistic features and metadata associated with the tweets, and employs hybrid crowdsensing over Twitter to build a strong ground-truth.

Identifying Witness Accounts from Social Media Using Imagery

This research investigates the use of image category classification to distinguish images posted to social media that are Witness Accounts of an event, using a bag-of-words method to create a vocabulary of visual words and classifier trained to categorize the encoded images.

Understanding eyewitness reports on Twitter during disasters

This work investigates the sources of tweets and classifies them into three types (i) direct eyewitnesses, (ii) indirect eyewitness, and (iii) vulnerable accounts, and investigates various characteristics associated with each kind of eyewitness account.

Verifying Baselines for Crisis Event Information Classification on Twitter

This paper seeks to make 3 contributions: the replication and results confirmation of a leading (and generalisable) technique; testing straightforward modifications of the technique likely to improve performance; and the extension of the method to a novel and complimentary type of crisis-relevant information to demonstrate it’s generalisability.

Autonomous Eyewitness Identification by Employing Linguistic Rules for Disaster Events

The lan-guage structure, linguistics, and word relation are utilized to achieve automatic extraction of feature-words by creating grammar rules and all identi fi ed features were implemented which were left out by the state-of-the-art model.

Testing the event witnessing status of micro-bloggers from evidence in their micro-blogs

Methods to filter and extract evidence using automated and semi-automated means and an implementation to test extracted evidence using Dempster Shafer Theory of Evidence are presented indicate that the inclusion of evidence from micro-blog text and linked image content can increase the number of micro- bloggers identified at events.

Mining social media for newsgathering: A review

  • A. Zubiaga
  • Computer Science
    Online Soc. Networks Media
  • 2019

Automatic Classification of Eyewitness Messages for Disaster Events Using Linguistic Rules and ML/AI Approaches

This work added more features and fine-tuned the Linguistic Rules to identify feature words related to Twitter Eyewitness messages for Disaster events, named as LR-TED approach, which can process millions of tweets in real-time and is scalable to diverse events and unseen content.

"Breaking" Disasters: Predicting and Characterizing the Global News Value of Natural and Man-made Disasters

A model for automatically identifying events from local news sources that may break on a global scale within the next 24 hours is proposed and can be used in a predictive setting to help journalists manage their sources more effectively, or in a descriptive manner to analyze media coverage of disasters.



Towards credibility of micro-blogs: characterising witness accounts

Information about events can be opportunistically harvested from social media, however, a major challenge is assessing the credibility of the information derived, and the credibility of the

Automatic detection of rumor on Sina Weibo

This is the first study on rumor analysis and detection on Sina Weibo, China's leading micro-blogging service provider, and examines an extensive set of features that can be extracted from the microblogs, and trains a classifier to automatically detect the rumors from a mixed set of true information and false information.

Finding Eyewitness Tweets During Crises

Disaster response agencies incorporate social media as a source of fast-breaking information to understand the needs of people affected by the many crises that occur around the world. These agencies

Information credibility on twitter

There are measurable differences in the way messages propagate, that can be used to classify them automatically as credible or not credible, with precision and recall in the range of 70% to 80%.

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.

Finding and assessing social media information sources in the context of journalism

This paper develops and investigates new methods for filtering and assessing the verity of sources found through social media by journalists, and takes a human centered design approach to developing a system, SRSR ("Seriously Rapid Source Review"), informed by journalistic practices and knowledge of information production in events.

Text-Based Twitter User Geolocation Prediction

This paper presents an integrated geolocation prediction framework, and evaluates the impact of nongeotagged tweets, language, and user-declared metadata on geolocated prediction, and discusses how users differ in terms of their geolocatability.

TwitterMonitor: trend detection over the twitter stream

TwitterMonitor, a system that performs trend detection over the Twitter stream and provides meaningful analytics that synthesize an accurate description of each topic on Twitter in real time, is presented.

You are where you tweet: a content-based approach to geo-locating twitter users

A probabilistic framework for estimating a Twitter user's city-level location based purely on the content of the user's tweets, which can overcome the sparsity of geo-enabled features in these services and enable new location-based personalized information services, the targeting of regional advertisements, and so on.

A Neural Probabilistic Language Model

This work proposes to fight the curse of dimensionality by learning a distributed representation for words which allows each training sentence to inform the model about an exponential number of semantically neighboring sentences.