Crisis-related Tweets Research Articles

Knowledge-injected prompt learning for actionable information extraction from crisis-related tweets

In crisis situations, emergency response organizations can derive significant benefits from actionable information available on social media. Such information provides effective guidance and support for rescue operations. Unlike traditional sources of information, social media reflects the latest developments during a crisis, as well as actionable suggestions and the needs of affected individuals. However, existing methods that leverage pre-trained language models for this task require a large amount of annotated data for fine-tuning. This data acquisition process is costly and impractical in some data-scarce scenarios. To address this challenge, we propose a Knowledge-injected Actionable Information Extraction Model (KAIEM) that can extract actionable information from crisis-related tweets in few-shot and zero-shot settings. Based on prompt learning, KAIEM automatically constructs the label word space of verbalizers using word embeddings, eliminating the need for manual design or external knowledge bases. This mechanism enables our model to make accurate predictions without relying on labeled data for fine-tuning. Additionally, KAIEM employs knowledge probing to inject conceptual knowledge into prompt templates, thereby enhancing the semantics of crisis-related tweets. We conducted a series of experiments on a real-world crisis-related dataset. The experimental results demonstrate the effectiveness of KAIEM in few-shot and zero-shot scenarios.

Unveiling the dynamics of crisis events: Sentiment and emotion analysis via multi-task learning with attention mechanism and subject-based intent prediction

In the age of rapid internet expansion, social media platforms like Twitter have become crucial for sharing information, expressing emotions, and revealing intentions during crisis situations. They offer crisis responders a means to assess public sentiment, attitudes, intentions, and emotional shifts by monitoring crisis-related tweets. To enhance sentiment and emotion classification, we adopt a transformer-based multi-task learning (MTL) approach with attention mechanism, enabling simultaneous handling of both tasks, and capitalizing on task interdependencies. Incorporating attention mechanism allows the model to concentrate on important words that strongly convey sentiment and emotion. We compare three baseline models, and our findings show that BERTweet outperforms the standard BERT model and exhibits similar performance to RoBERTa in crisis tweets. Furthermore, we employ natural language processing techniques to extract key subject entities (e.g., police, victims) and leverage the publicly available commonsense knowledge model, COMET-ATOMIC 2020, to identify their intentions in given crisis scenarios. Evaluation of COMET-ATOMIC 2020 on subject-based intent prediction in crisis tweets reveals that BART was superior to GPT2-XL model, providing crisis responders with vital information for better decision making. Notably, the integration of sentiment and emotion classification, identification of attention words and subject-based intent prediction represents a novel methodology, not previously applied in the context of crisis scenarios.

Hybrid Bat and Salp Swarm Algorithm for Feature Selection and Classification of Crisis-Related Tweets in Social Networks

Hybrid Bat and Salp Swarm Algorithm for Feature Selection and Classification of Crisis-Related Tweets in Social Networks

Exploring Temporal and Multilingual Dynamics of Post-Disaster Social Media Discourse: A Case of Fukushima Daiichi Nuclear Accident

The 2011 Fukushima Daiichi nuclear disaster has led to worldwide disruptive discussions related to crisis. In April 2021, the news that the Japanese Cabinet decided to discharge the stored wastewater into the Pacific Ocean drew global attention once again. Social media platforms like Twitter are ubiquitously used to gain information and exchange opinions during and after a crisis. Analyzing crisis-related tweets can help capture insights for public situational awareness development, crisis global response coordination, and post-disaster policy-making. We examined corresponding Twitter discourse in different languages about the nuclear disaster in 2011 and the follow-up discharge of the stored water until 2021. We utilized NLP techniques including topic modeling and sentiment analysis to identify the dominant topics related to the nuclear disaster, the post-disaster discourses, and the public attitudes towards these topics in different time phases. Our work revealed multilingual disparities of post-disaster discourse dynamics and the regional public attitudes towards the post-disaster management in the long run.

Classifying informative and non-informative tweets from the twitter by adapting image features during disaster

During the crisis, people post a large number of informative and non-informative tweets on Twitter. Informative tweets provide helpful information such as affected individuals, infrastructure damage, availability and resource requirements, etc. In contrast, non-informative tweets do not provide helpful information related to either humanitarian organizations or victims. Identifying informative tweets is a challenging task during the disaster. People often post images along with text on Twitter during the disaster. In addition to tweet text features, image features are also crucial for identifying informative tweets. However, existing methods use only text features but do not use image features to identify crisis-related tweets during the disaster. This paper proposes a novel approach by considering the image features along with the text features. It includes a text-based classification model, an image-based classification model and a late fusion. The text-based classification model uses the Convolutional Neural Network (CNN) and the Artificial Neural Network (ANN). CNN is used to extract text features from a tweet and the ANN is used to classify tweets based on extracted text features of CNN. The image-based classification model uses the fine-tuned VGG-16 architecture to extract the image features from the image and classify the image in a tweet. The output of the text-based classification model and the image-based classification model are combined using the late fusion technique to predict the tweet label. Extensive experiments are carried out on Twitter datasets of various crises, such as the Mexico earthquake, California Wildfires, etc., to demonstrate the effectiveness of the proposed method. The proposed method outperforms the state-of-the-art methods on various parameters to identify informative tweets during the disaster.

Automatic analysis of microblogging data to aid in emergency management

Microblogging platforms like Twitter, in the recent years, have become one of the important sources of information for a wide spectrum of users. As a result, these platforms have become great resources to provide support for emergency management. During any crisis, it is necessary to sieve through a huge amount of social media texts within a short span of time to extract meaningful information from them. Extraction of emergency-specific information, such as topic keywords or landmarks or geo-locations of sites, from these texts plays a significant role in building an application for emergency management. This paper thus highlights different aspects of automatic analysis of tweets to help in developing such an application. Hence, it focuses on: (1) identification of crisis-related tweets using machine learning, (2) exploration of topic model implementations and looking at its effectiveness on short messages (as short as 140 characters); and performing an exploratory data analysis on short texts related to crises collected from Twitter, and looking at different visualizations to understand the commonality and differences between topics and different crisis-related data, and (3) providing a proof of concept for identifying and retrieving different geo-locations from tweets and extracting the GPS coordinates from this data to approximately plot them in a map.

Content features of tweets for effective communication during disasters: A media synchronicity theory perspective

Users’ ability to retweet information has made Twitter one of the most prominent social media platforms for disseminating emergency information during disasters. However, few studies have examined how Twitter’s features can support the different communication patterns that occur during different phases of disaster events. Based on the literature of disaster communication and Media Synchronicity Theory, we identify distinct disaster phases and the two communication types—crisis communication and risk communication—that occur during those phases. We investigate how Twitter’s representational features, including words, URLs, hashtags, and hashtag importance, influence the average retweet time—that is, the average time it takes for retweet to occur—as well as how such effects differ depending on the type of disaster communication. Our analysis of tweets from the 2013 Colorado floods found that adding more URLs to tweets increases the average retweet time more in risk-related tweets than it does in crisis-related tweets. Further, including key disaster-related hashtags in tweets contributed to faster retweets in crisis-related tweets than in risk-related tweets. Our findings suggest that the influence of Twitter’s media capabilities on rapid tweet propagation during disasters may differ based on the communication processes.

Public Frame Building: The Role of Source Usage in Times of Crisis

New media have markedly enhanced the public’s capacity to influence the framing of an issue, especially within crisis situations. By relying on research triangulation, this study aims to map the comprehensive frame-building process of the public as an understudied domain within framing and crisis research. Study 1 uses advanced automated content analyses of crisis-related tweets ( N = 252,711) to examine how the public built frames online with the use of information sources. Study 2 applies an innovative vignette study ( N = 772) to investigate the conditions that influence the public’s source selection during crises. The findings illustrate how the public uses sources to address certain frame functions and show that source usage is subject to external factors (i.e., crisis origin and magnitude) as well as internal factors (i.e., crisis involvement and habitual source use).