More Like this

1. A Twitter Data Credibility Framework—Hurricane Harvey as a Use Case

   https://doi.org/10.3390/ijgi8030111  

   Yang, Jingchao ; Yu, Manzhu ; Qin, Han ; Lu, Mingyue ; Yang, Chaowei ( March 2019 , ISPRS International Journal of Geo-Information)

   Social media data have been used to improve geographic situation awareness in the past decade. Although they have free and openly availability advantages, only a small proportion is related to situation awareness, and reliability or trustworthiness is a challenge. A credibility framework is proposed for Twitter data in the context of disaster situation awareness. The framework is derived from crowdsourcing, which states that errors propagated in volunteered information decrease as the number of contributors increases. In the proposed framework, credibility is hierarchically assessed on two tweet levels. The framework was tested using Hurricane Harvey Twitter data, in which situation awareness related tweets were extracted using a set of predefined keywords including power, shelter, damage, casualty, and flood. For each tweet, text messages and associated URLs were integrated to enhance the information completeness. Events were identified by aggregating tweets based on their topics and spatiotemporal characteristics. Credibility for events was calculated and analyzed against the spatial, temporal, and social impacting scales. This framework has the potential to calculate the evolving credibility in real time, providing users insight on the most important and trustworthy events. 

   more » « less
2. Estimating Hourly Population Distribution Patterns at High Spatiotemporal Resolution in Urban Areas Using Geo-Tagged Tweets and Dasymetric Mapping

   https://doi.org/10.4230/LIPIcs.GIScience.2021.I.10  

   Park, Jaehee ( September 2020 , 11th International Conference on Geographic Information Science (GIScience 2021))

   null (Ed.)

   This paper introduces a spatiotemporal analysis framework for estimating hourly changing population distribution patterns in urban areas using geo-tagged tweets (the messages containing users’ geospatial locations), land use data, and dasymetric maps. We collected geo-tagged social media (tweets) within the County of San Diego during one year (2015) by using Twitter’s Streaming Application Programming Interfaces (APIs). A semi-manual Twitter content verification procedure for data cleaning was applied first to separate tweets created by humans from non-human users (bots). The next step was to calculate the number of unique Twitter users every hour within census blocks. The final step was to estimate the actual population by transforming the numbers of unique Twitter users in each census block into estimated population densities with spatial and temporal factors using dasymetric maps. The temporal factor was estimated based on hourly changes of Twitter messages within San Diego County, CA. The spatial factor was estimated by using the dasymetric method with land use maps and 2010 census data. Comparing to census data, our methods can provide better estimated population in airports, shopping malls, sports stadiums, zoo and parks, and business areas during the day time. 

   more » « less
3. A System Analytics Framework for Detecting Infrastructure-Related Topics in Disasters Using Social Sensing

   Fan, Chao ; Mostafavi, Ali ; Gupta, Aayush ; Zhang, Cheng ( January 2018 , 25th International Workshop on Intelligent Computing in Engineering (EG-ICE))

   The objective of this paper is to propose and test a system analytics framework based on social sensing and text mining to detect topic evolution associated with the performance of infrastructure systems in disasters. Social media, like Twitter, as active channels of communication and information dissemination, provide insights into real-time information and first-hand experience from affected areas in mass emergencies. While the existing studies show the importance of social sensing in improving situational awareness and emergency response in disasters, the use of social sensing for detection and analysis of infrastructure systems and their resilience performance has been rather limited. This limitation is due to the lack of frameworks to model the events and topics (e.g., grid interruption and road closure) evolution associated with infrastructure systems (e.g., power, highway, airport, and oil) in times of disasters. The proposed framework detects infrastructure-related topics of the tweets posted in disasters and their evolutions by integrating searching relevant keywords, text lemmatization, Part-of-Speech (POS) tagging, TF-IDF vectorization, topic modeling by using Latent Dirichlet Allocation (LDA), and K-Means clustering. The application of the proposed framework was demonstrated in a study of infrastructure systems in Houston during Hurricane Harvey. In this case study, more than sixty thousand tweets were retrieved from 150-mile radius in Houston over 39 days. The analysis of topic detection and evolution from user-generated data were conducted, and the clusters of tweets pertaining to certain topics were mapped in networks over time. The results show that the proposed framework enables to summarize topics and track the movement of situations in different disaster phases. The analytics elements of the proposed framework can improve the recognition of infrastructure performance through text-based representation and provide evidence for decision-makers to take actionable measurements. 

   more » « less
4. A Comparison Study for Disaster Tweet Classification Using Deep Learning Models

   https://doi.org/10.5220/0012129300003541  

   Dinani, Soudabeh ; Caragea, Doina ( January 2023 , Proceedings of the 12th International Conference on Data Science, Technology and Applications DATA)

   Effectively filtering and categorizing the large volume of user-generated content on social media during disaster events can help emergency management and disaster response prioritize their resources. Deep learning approaches, including recurrent neural networks and transformer-based models, have been previously used for this purpose. Capsule Neural Networks (CapsNets), initially proposed for image classification, have been proven to be useful for text analysis as well. However, to the best of our knowledge, CapsNets have not been used for classifying crisis-related messages, and have not been extensively compared with state-of-the-art transformer-based models, such as BERT. Therefore, in this study, we performed a thorough comparison between CapsNet models, state-of-the-art BERT models and two popular recurrent neural network models that have been successfully used for tweet classification, specifically, LSTM and Bi-LSTM models, on the task of classifying crisis tweets both in terms of their informativeness (binary classification), as well as their humanitarian content (multi-class classification). For this purpose, we used several benchmark datasets for crisis tweet classification, namely CrisisBench, CrisisNLP and CrisisLex. Experimental results show that the performance of the CapsNet models is on a par with that of LSTM and Bi-LSTM models for all metrics considered, while the performance obtained with BERT models have surpassed the performance of the other three models across different datasets and classes for both classification tasks, and thus BERT could be considered the best overall model for classifying crisis tweets. 

   more » « less
5. Analyzing the Sentiment of Crowd for Improving the Emergency Response Services

   https://doi.org/10.1109/SMARTCOMP.2018.00067  

   Singh, Neha ; Roy, Nirmalya ; Gangopadhyay, Aryya ( June 2018 , 2018 IEEE International Conference on Smart Computing (SMARTCOMP))

   Twitter is an extremely popular micro-blogging social platform with millions of users, generating thousands of tweets per second. The huge amount of Twitter data inspire the researchers to explore the trending topics, event detection and event tracking which help to postulate the fine-grained details and situation awareness. Obtaining situational awareness of any event is crucial in various application domains such as natural calamities, man made disaster and emergency responses. In this paper, we advocate that data analytics on Twitter feeds can help improve the planning and rescue operations and services as provided by the emergency personnel in the event of unusual circumstances. We take a different approach and focus on the users' emotions, concerns and feelings expressed in tweets during the emergency situations, and analyze those feelings and perceptions in the community involved during the events to provide appropriate feedback to emergency responders and local authorities. We employ sentiment analysis and change point detection techniques to process, discover and infer the spatiotemporal sentiments of the users. We analyze the tweets from recent Las Vegas shooting (Oct. 2017) and note that the changes in the polarity of the sentiments and articulation of the emotional expressions, if captured successfully can be employed as an informative tool for providing feedback to EMS. 

   more » « less