Identifying Bursty Local Areas Related To Emergency Topics

2017 IEEE International Conference on Big Data (Big Data), 2017

Social media can be an invaluable help in a mass emergency, but the information handling can be challenging. One major concern is identifying posts related to the area, or pinning them on a map. This exploratory study analyzes the spatial data coming with tweets during two natural disasters, an earthquake and a hurricane. Geo-tagged tweets confirm to be a small fraction of all tweets and disasters within a limited region appear to be a niche topic in the whole stream. The results can help researchers and practitioners in the design of tools to identify these messages.

Social media is a platform to express one's view in real time. This real time nature of social media makes it an attractive tool for disaster management, as both victims and officials can put their problems and solutions at the same place in real time. We investigate the Twitter post in a flood related disaster and propose an algorithm to identify victims asking for help. The developed system takes tweets as inputs and categorizes them into high or low priority tweets. User location of high priority tweets with no location information is predicted based on historical locations of the users using the Markov model. The system is working well, with its classification accuracy of 81%, and location prediction accuracy of 87%. The present system can be extended for use in other natural disaster situations, such as earthquake, tsunami, etc., as well as man-made disasters such as riots, terrorist attacks etc. The present system is first of its kind, aimed at helping victims during disasters based on their tweets.

International Journal of Geographical Information Science, 2015

n recent years, social media emerged as a potential resource to improve the management of crisis situations such as disasters triggered by natural hazards. Although there is a growing research body concerned with the analysis of the usage of social media during disasters, most previous work has concentrated on using social media as a standalone information source, whereas its combination with other information sources holds a still underexplored potential. This paper presents an approach to enhance the identification of relevant messages from social media that relies upon the relations between georeferenced social media messages as Volunteered Geographic Information, and geographic features of flood phenomena as derived from authoritative data (sensor data, hydrological data and digital elevation models). We apply this approach to examine the micro- blogging text messages of the Twitter platform (tweets) produced during the River Elbe Flood of June 2013 in Germany. This is performed by means of a statistical analysis aimed at identifying general spatial patterns in the occurrence of flood-related tweets that may be associated with proximity to and severity of flood events. The results show that messages near (up to 10 km) to severely flooded areas have a much higher probability of being related to floods. In this manner, we conclude that the geographic approach proposed here provides a reliable quantitative indicator of the usefulness of messages from social media by leveraging existing knowledge about natural hazards such as floods, thus being valuable for disaster management in both crisis response and preventive monitoring.

Social media such as micro blogging services have a significant impact on the day-today lives of people. These services are currently being used by government agencies to interact and communicate information to general public. They also bring an effective collaboration of all stakeholders for dissemination of information during an emergency. Social media is capable of providing spontaneous information during emergency/disaster situations unlike news media, therefore, particularly micro blogging services, have the potential to be adopted as an additional tool for emergency services. In the present work the authors by mining real time data from twitter TM tried to predict the impending damage in the following days during flood scenario. The users of twitter provide important information such as warnings, location of an event, first hand experiences. Such information is collected, preprocessed, geo located and filtered. From the collected information, geo-coded data is prioritized to that of text data. Then the data is analyzed to find the course of the disaster through regression analysis. Later, disaster curve is extrapolated for prediction of damage susceptible locations in the following days. The results are validated by analyzing the past events. In this study, 2015 Chennai flood data is used to validate the results. The study has the potential to facilitate disaster managers for better response operations during emergencies.

New media are increasingly used to capture ambient and volunteered geographic information in multiple contexts, from mapping the evolution of the social movements to tracking infectious disease. The social media platform Twitter is popular for these applications; it boasts over 500 million messages ('tweets') generated every day from as many total users at an average rate of 5,700 messages per second. In the United States, Japan, and Chile to name a few, Twitter is officially and unofficially used as an emergency notification and response system in the event of earthquakes, wildfires, and prescribed fires. A prototype for operational emergency detections from social media, specifically Twitter, was created using natural language processing and information retrieval techniques. The intent is to identify and locate emergency situations in the contiguous United States, namely prescribed fires, wildfires, and earthquakes, that are often missed by satellite detections. The authors present their methodologies and an evaluation of performance in collecting relevant tweets, extracting metrics such as area affected and geo-locating the events. Lessons learned from data mining Twitter for spatiotemporally-explicit information are included to inform future data mining research and applications.

IRJET, 2020

Social media has become a place where people meet, greet and share vast information and their personal views. It is a very useful source for procuring vital information in emergency situations. One such platform is Twitter which is a micro-blogging and social networking service where a large number of people from celebrities to common people express their views and opinions and share information. We could use this information to mitigate and extract useful information from messages in Twitter called as tweets. We developed a system takes input as tweets from hashtag provided by the user and categories them into relevant and non-relevant using Naïve Bayes algorithm. These relevant tweets contain data that is crucial for any emergency situation management. These classified tweets are further prioritized by XGBoost algorithm, which determines the tweets that are most important during such situations. In the final stage the user can click on the tweet by which they can see all the key details of the tweet such as user name, user location and other such information to take suitable action on the situation.

Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18

Hurricane evacuation is a complex process and a better understanding of the evacuation behavior of the coastal residents could be helpful in planning better evacuation policy. Traditionally, various aspects of the household evacuation decisions have been determined by post-evacuation questionnaire surveys, which are usually time-consuming and expensive. Increased activity of users on social media, especially during emergencies, along with the geo-tagging of the posts, provides an opportunity to gain insights into user's decision-making process, as well as to gauge public opinion and activities using the social media data as a supplement to the traditional survey data. This paper leverages the geo-tagged Tweets posted in the New York City (NYC) in wake of Hurricane Sandy to understand the evacuation behavior of the residents. Based on the geo-tagged Tweet locations, we classify the NYC Twitter users into one of the three categories: outside evacuation zone, evacuees, and non-evacuees and examine the types of Tweets posted by each group during different phases of the hurricane. We establish a strong link between the social connectivity with the decision of the users to evacuate or stay. We analyze the geo-tagged Tweets to understand evacuation and return time and evacuation location patterns of evacuees. The analysis presented in this paper could be useful for authorities to plan a better evacuation campaign to minimize the risk to the life of the residents of the emergency hit areas. CCS CONCEPTS • Information systems → Mobile information processing systems; • Networks → Social media networks; • Human-centered computing → Social media;

2016

Crisis management systems would benefit from exploiting human observations of disaster sites shared in near-real time via microblogs, however, utterly require location information in order to make use of these. Whereas the popularity of microblogging services, such as Twitter, is on the rise, the percentage of GPS-stamped Twitter microblog articles (i.e., tweets) is stagnating. Geo-coding techniques, which extract location information from text, represent a promising means to overcome this limitation. However, whereas geo-coding of news articles represents a well-studied area, the brevity, informal nature and lack of context encountered in tweets introduces novel challenges on their geo-coding. Few efforts so far have been devoted to analyzing the different types of geographical information users mention in tweets, and the challenges of geo-coding these in the light of omitted context by exploiting situative information. To overcome this limitation, we propose a gold-standard corpus...

Various studies have presented ways of approximating the location of tweets through performing text mining techniques on the contents of tweets. Methodologies of this type create word density based models for each computa-tionally or geopolitically defined region. Incoming tweets are then compared against the text models of the defined regions to find which region the new tweet most probably comes from. These studies assume that each region can be distinguished by the distribution of tokens in each respective regional word model. This study proposes a new approach to approximating the location of tweets under a similarly valid assumption–that semantically similar tweets occur in geographically close locations. This is done through modeling text content of tweets in a semantic space and geo-tagging tweets down to the granularity of latitude and longitude coordinates using a new algorithm for location approximation. Through using a common method for semantic mod-eling such as Latent Semantic Analysis, this study provides a baseline for semantic similarity based location approximation from which more state of the art and tweet specific semantic modeling methods can develop from. Moreover, this pioneering method for latitude-longitude granularity location approximation paves the way for more innovative research that deviates from the commonly implemented location approximation to defined regions.

Proceedings of the ACM SIGMOD Workshop on Databases and Social Networks - DBSocial '13, 2013

Unprecedented success and active usage of social media services result in massive amounts of user-generated data. An increasing interest in the contained information from social media data leads to more and more sophisticated analysis and visualization applications. Because of the fast pace and distribution of news in social media data it is an appropriate source to identify events in the data and directly display their occurrence to analysts or other users. This paper presents a method for event identification in local areas using the Twitter data stream. We implement and use a combined log-likelihood ratio approach for the geographic and time dimension of real-life Twitter data in predefined areas of the world to detect events occurring in the message contents. We present a case study with two interesting scenarios to show the usefulness of our approach.