Filters








1,393 Hits in 11.6 sec

Information Abstraction from Crises Related Tweets Using Recurrent Neural Network [chapter]

Mehdi Ben Lazreg, Morten Goodwin, Ole-Christoffer Granmo
2016 IFIP Advances in Information and Communication Technology  
This papers presents a first step towards an approach for information extraction from large Twitter data.  ...  The information shared about a crisis in social media is massive, complex, informal and heterogeneous, which makes extracting useful information a difficult task.  ...  This papers presents a first step towards an approach for information extraction from large Twitter data collections.  ... 
doi:10.1007/978-3-319-44944-9_38 fatcat:v26q7uv4ufbd5pd7imwa33ubzm

A Pipeline for Rapid Post-Crisis Twitter Data Acquisition, Filtering and Visualization

Mayank Kejriwal, Yao Gu
2019 Technologies  
In this paper, we present such a pipeline for facilitating immediate post-crisis data collection, curation and relevance filtering from the Twitter API.  ...  from free, publicly available streams like the Twitter API in the immediate aftermath of a crisis.  ...  Another example of extracting situational awareness from Twitter using NLP methods was presented by Verma et al. [10] .  ... 
doi:10.3390/technologies7020033 fatcat:im7licae2fazla6lfq6335tvee

A Pipeline for Post-Crisis Twitter Data Acquisition [article]

Mayank Kejriwal, Yao Gu
2018 arXiv   pre-print
In this paper, we present ongoing work on a pipeline for facilitating immediate post-crisis data collection, curation and relevance filtering from the Twitter API.  ...  from free, publicly available streams like the Twitter API.  ...  First, we present ongoing work on a simple and scalable end-to-end pipeline that ingests data from the Twitter streaming API and uses a combination of unsupervised text embeddings and limited-label active  ... 
arXiv:1801.05881v1 fatcat:g4vdr4g7jfhjbdnni4zqpe7pl4

Sentiment Severity on Location-Based Social Network (LBSN) Data of Natural disasters

2020 International journal of recent technology and engineering  
In this paper, the lexical analysis to sentiment analysis of twitter data is employed.  ...  This paper proposes a methodology to extract relevant sentiment information from Location Based Social Network (LBSN) and suggests a unique scale to classify this information to help disaster management  ...  From the entire data set collected from twitter API only the tweets with geospatial information, which is from India dated from 03 rd May 2019 to 06 th May 2019 were analyzed.  ... 
doi:10.35940/ijrte.e6631.018520 fatcat:zsim6uslrneqnmoqdkoq7zu57q

Rapid geotagging and disambiguation of social media text via an indexed gazetteer

Evan A. Sultanik, Clayton Fink
2012 International Conference on Information Systems for Crisis Response and Management  
We argue that such fast, high precision, unsupervised approaches are needed when important, actionable information is required from noisy data sources such as Twitter.  ...  In this paper, we demonstrate a new technique, RapidGeo, for extracting and disambiguating place names from a location specific Twitter feed using an unsupervised technique for tagging location mentions  ...  Using automated techniques for extracting location references from Twitter data during a crisis via supervised learning-even if using training data from Twitter during a previous, yet similar incident-may  ... 
dblp:conf/iscram/SultanikF12 fatcat:l75ilnhr2ze23j4nmgernrwvci

Unsupervised Detection of Sub-events in Large Scale Disasters [article]

Chidubem Arachie, Manas Gaur, Sam Anzaroot, William Groves, Ke Zhang, Alejandro Jaimes
2019 arXiv   pre-print
We first extract noun-verb pairs and phrases from raw tweets as sub-event candidates.  ...  In particular, we present a novel, unsupervised learning framework to detect sub-events in Tweets for retrospective crisis analysis.  ...  Conclusion A straightforward approach to sub-event identification has been described using publicly available large scale crisis data from Twitter.  ... 
arXiv:1912.13332v1 fatcat:6qn523flrjfubkffgwcwrfyzd4

Unsupervised Detection of Sub-Events in Large Scale Disasters

Chidubem Arachie, Manas Gaur, Sam Anzaroot, William Groves, Ke Zhang, Alejandro Jaimes
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We first extract noun-verb pairs and phrases from raw tweets as sub-event candidates.  ...  In particular, we present a novel, unsupervised learning framework to detect sub-events in Tweets for retrospective crisis analysis.  ...  Conclusion A straightforward approach to sub-event identification has been described using publicly available large scale crisis data from Twitter.  ... 
doi:10.1609/aaai.v34i01.5370 fatcat:lp7j3ci5mbhffatpvnfhgslgdq

Processing Social Media Messages in Mass Emergency

Muhammad Imran, Carlos Castillo, Fernando Diaz, Sarah Vieweg
2015 ACM Computing Surveys  
Research thus far has, to a large extent, produced methods to extract situational awareness information from social media.  ...  These challenges can be mapped to classical information processing operations such as filtering, classifying, ranking, aggregating, extracting, and summarizing.  ...  ACKNOWLEDGMENTS We are thankful to Jakob Rogstadius and Per Aarvik, who pointed us to historical information.  ... 
doi:10.1145/2771588 fatcat:fb6bypzs6zdqznxv4maltpxvqq

Unsupervised Text Mining of COVID-19 Records [article]

Mohamad Zamini
2021 arXiv   pre-print
According to the high volume of data production on social networks, automated text mining approaches can help search, read and summarize helpful information.  ...  Twitter as a powerful tool can help researchers measure public health in response to COVID-19.  ...  With 500 million Tweets sent each day, Twitter is a source of information extraction relating to any crisis.  ... 
arXiv:2110.07357v1 fatcat:iqbnvja6ureynabsh7fcfsa5um

Unsupervised and Interpretable Domain Adaptation to Rapidly Filter Tweets for Emergency Services [article]

Jitin Krishnan, Hemant Purohit, Huzefa Rangwala
2020 arXiv   pre-print
In this paper, we hypothesize that unsupervised domain adaptation through multi-task learning can be a useful framework to leverage data from past crisis events for training efficient information filtering  ...  During the onset of a disaster event, filtering relevant information from the social web data is challenging due to its sparse availability and practical limitations in labeling datasets of an ongoing  ...  CONCLUSION We presented a novel approach of unsupervised domain adaptation with multi-task learning to classify relevant information from Twitter streams for crisis management, while addressing the problems  ... 
arXiv:2003.04991v2 fatcat:3pm3ow2uina6jmiaphznx674yq

Blockchain-based Event Detection and Trust Verification Using Natural Language Processing and Machine Learning

Zeinab Shahbazi, Yung-Cheol Byun
2021 IEEE Access  
The event identification uses real-time data from social networks. Automatic reasoning extracts the information and knowledge from accessible data using intelligent techniques.  ...  Figure 1 presents the overview architecture of crisis event detection in term of supervised and unsupervised learning based on collected data source.  ... 
doi:10.1109/access.2021.3139586 fatcat:k2r24g4yzzgstjuypud7sxlzyi

Processing Social Media Messages in Mass Emergency: A Survey [article]

Muhammad Imran, Carlos Castillo, Fernando Diaz, Sarah Vieweg
2015 arXiv   pre-print
These challenges can be mapped to classical information processing operations such as filtering, classifying, ranking, aggregating, extracting, and summarizing.  ...  We examine the particularities of this setting, and then methodically examine a series of key sub-problems ranging from the detection of events to the creation of actionable and useful summaries.  ...  For instance, in Sultanik and Fink [2012], authors proposed an unsupervised approach to extract and disambiguate location mentions in Twitter messages during crisis situations.  ... 
arXiv:1407.7071v3 fatcat:e7mcvae5freddaus7ndolygeti

How Social Media Text Analysis Can Inform Disaster Management [chapter]

Sabine Gründer-Fahrer, Antje Schlaf, Sebastian Wustmann
2018 Lecture Notes in Computer Science  
The aim is to show how state-of-the-art techniques from text mining and information extraction can be applied to fulfil the requirements of the end-users.  ...  Digitalization and the rise of social media have led disaster management to the insight that modern information technology will have to play a key role in dealing with a crisis.  ...  The research leading to these results has received funding from the European Union's Seventh Framework Programme under grant agreement No. 607691 (SLANDAIL).  ... 
doi:10.1007/978-3-319-73706-5_17 fatcat:st3cqjy2jbabzmtz7ocx2qmhni

A REVIEW ON SENTIMENT ANALYSIS OF SOCIAL MEDIA DATA USING TEXT MINING AND MACHINE LEARNING

GURPREET KAUR, MANOJ KUMAR
2016 International Journal of Advanced Research  
Sentiment analysis does not only deal with extracting polarity but also deals with extracting features from the text.  ...  Sentiment analysis is a natural language processing and information extraction task. This technique aims to extract writer"s feelings expressed in comments or reviews.  ... 
doi:10.21474/ijar01/526 fatcat:hbnk3dtcbnaahf3aots2gnax6a

Keyphrase Extraction from Disaster-related Tweets

Jishnu Ray Chowdhury, Cornelia Caragea, Doina Caragea
2019 The World Wide Web Conference on - WWW '19  
Twitter data.  ...  While keyphrase extraction has received considerable attention in recent years, relatively few studies exist on extracting keyphrases from social media platforms such as Twitter, and even fewer for extracting  ...  We also thank NSF for support from the grants IIS-1526542, IIS-1423337, IIS-1652674, and CMMI-1541155.  ... 
doi:10.1145/3308558.3313696 dblp:conf/www/ChowdhuryCC19 fatcat:fgir6ach3bcbhkz7lyvuj7hvxa
« Previous Showing results 1 — 15 out of 1,393 results