狠狠撸shows by User: mimran15
/
http://www.slideshare.net/images/logo.gif狠狠撸shows by User: mimran15
/
Wed, 25 Apr 2018 12:55:50 GMT狠狠撸Share feed for 狠狠撸shows by User: mimran15Processing Social Media Messages in Mass Emergency: A Survey
/slideshow/processing-social-media-messages-in-mass-emergency-a-survey-94984592/94984592
final2www18surveypaper-180425125551 Millions of people use social media to share information during disasters and mass emergencies. Information available on social media, particularly in the early hours of an event when few other sources are available, can be extremely valuable for emergency responders and decision makers, helping them gain situational awareness and plan relief efforts. Processing social media content to obtain such information involves solving multiple challenges, including parsing brief and informal messages, handling information overload, and prioritizing different types of information. These challenges can be mapped to information processing operations such as filtering, classifying, ranking, aggregating, extracting, and summarizing. This work highlights these challenges and presents state of the art computational techniques to deal with social media messages, focusing on their application to crisis scenarios.]]>
Millions of people use social media to share information during disasters and mass emergencies. Information available on social media, particularly in the early hours of an event when few other sources are available, can be extremely valuable for emergency responders and decision makers, helping them gain situational awareness and plan relief efforts. Processing social media content to obtain such information involves solving multiple challenges, including parsing brief and informal messages, handling information overload, and prioritizing different types of information. These challenges can be mapped to information processing operations such as filtering, classifying, ranking, aggregating, extracting, and summarizing. This work highlights these challenges and presents state of the art computational techniques to deal with social media messages, focusing on their application to crisis scenarios.]]>
Wed, 25 Apr 2018 12:55:50 GMT/slideshow/processing-social-media-messages-in-mass-emergency-a-survey-94984592/94984592mimran15@slideshare.net(mimran15)Processing Social Media Messages in Mass Emergency: A Surveymimran15Millions of people use social media to share information during disasters and mass emergencies. Information available on social media, particularly in the early hours of an event when few other sources are available, can be extremely valuable for emergency responders and decision makers, helping them gain situational awareness and plan relief efforts. Processing social media content to obtain such information involves solving multiple challenges, including parsing brief and informal messages, handling information overload, and prioritizing different types of information. These challenges can be mapped to information processing operations such as filtering, classifying, ranking, aggregating, extracting, and summarizing. This work highlights these challenges and presents state of the art computational techniques to deal with social media messages, focusing on their application to crisis scenarios.<img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/final2www18surveypaper-180425125551-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> Millions of people use social media to share information during disasters and mass emergencies. Information available on social media, particularly in the early hours of an event when few other sources are available, can be extremely valuable for emergency responders and decision makers, helping them gain situational awareness and plan relief efforts. Processing social media content to obtain such information involves solving multiple challenges, including parsing brief and informal messages, handling information overload, and prioritizing different types of information. These challenges can be mapped to information processing operations such as filtering, classifying, ranking, aggregating, extracting, and summarizing. This work highlights these challenges and presents state of the art computational techniques to deal with social media messages, focusing on their application to crisis scenarios.
]]>
7346https://cdn.slidesharecdn.com/ss_thumbnails/final2www18surveypaper-180425125551-thumbnail.jpg?width=120&height=120&fit=boundspresentationBlackhttp://activitystrea.ms/schema/1.0/posthttp://activitystrea.ms/schema/1.0/posted0Damage Assessment from Social Media Imagery Data During Disasters
/slideshow/damage-assessment-from-social-media-imagery-data-during-disasters/78675870
fullpaperdamageassessment-170808192839 Rapid access to situation-sensitive data through social media networks creates new opportunities to address a number of real-world problems. Damage assessment during dis- asters is a core situational awareness task for many humanitarian organizations that traditionally takes weeks and months. In this work, we analyze images posted on social media platforms during natural disasters to determine the level of damage caused by the disasters. We employ state-of-the-art machine learning techniques to perform an extensive experimentation of damage assessment using images from four major natural disasters. We show that the domain-specific fine-tuning of deep Convolutional Neural Networks (CNN) outperforms other state-of-the-art techniques such as Bag-of-Visual-Words (BoVW). High classification ac- curacy under both event-specific and cross-event test settings demonstrate that the proposed approach can effectively adapt deep-CNN features to identify the severity of destruction from social media images taken after a disaster strike.
]]>
Rapid access to situation-sensitive data through social media networks creates new opportunities to address a number of real-world problems. Damage assessment during dis- asters is a core situational awareness task for many humanitarian organizations that traditionally takes weeks and months. In this work, we analyze images posted on social media platforms during natural disasters to determine the level of damage caused by the disasters. We employ state-of-the-art machine learning techniques to perform an extensive experimentation of damage assessment using images from four major natural disasters. We show that the domain-specific fine-tuning of deep Convolutional Neural Networks (CNN) outperforms other state-of-the-art techniques such as Bag-of-Visual-Words (BoVW). High classification ac- curacy under both event-specific and cross-event test settings demonstrate that the proposed approach can effectively adapt deep-CNN features to identify the severity of destruction from social media images taken after a disaster strike.
]]>
Tue, 08 Aug 2017 19:28:39 GMT/slideshow/damage-assessment-from-social-media-imagery-data-during-disasters/78675870mimran15@slideshare.net(mimran15)Damage Assessment from Social Media Imagery Data During Disastersmimran15Rapid access to situation-sensitive data through social media networks creates new opportunities to address a number of real-world problems. Damage assessment during dis- asters is a core situational awareness task for many humanitarian organizations that traditionally takes weeks and months. In this work, we analyze images posted on social media platforms during natural disasters to determine the level of damage caused by the disasters. We employ state-of-the-art machine learning techniques to perform an extensive experimentation of damage assessment using images from four major natural disasters. We show that the domain-specific fine-tuning of deep Convolutional Neural Networks (CNN) outperforms other state-of-the-art techniques such as Bag-of-Visual-Words (BoVW). High classification ac- curacy under both event-specific and cross-event test settings demonstrate that the proposed approach can effectively adapt deep-CNN features to identify the severity of destruction from social media images taken after a disaster strike.
<img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/fullpaperdamageassessment-170808192839-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> Rapid access to situation-sensitive data through social media networks creates new opportunities to address a number of real-world problems. Damage assessment during dis- asters is a core situational awareness task for many humanitarian organizations that traditionally takes weeks and months. In this work, we analyze images posted on social media platforms during natural disasters to determine the level of damage caused by the disasters. We employ state-of-the-art machine learning techniques to perform an extensive experimentation of damage assessment using images from four major natural disasters. We show that the domain-specific fine-tuning of deep Convolutional Neural Networks (CNN) outperforms other state-of-the-art techniques such as Bag-of-Visual-Words (BoVW). High classification ac- curacy under both event-specific and cross-event test settings demonstrate that the proposed approach can effectively adapt deep-CNN features to identify the severity of destruction from social media images taken after a disaster strike.
]]>
4615https://cdn.slidesharecdn.com/ss_thumbnails/fullpaperdamageassessment-170808192839-thumbnail.jpg?width=120&height=120&fit=boundspresentationBlackhttp://activitystrea.ms/schema/1.0/posthttp://activitystrea.ms/schema/1.0/posted0Image4Act: Online Social Media Image Processing for Disaster Response
/slideshow/image4act-online-social-media-image-processing-for-disaster-response/78659096
image4actasonamdemo-170808094818 We present an end-to-end social media image processing system called Image4Act. The system aims at collecting, denoising, and classifying imagery content posted on social media platforms to help humanitarian organizations in gaining situational awareness and launching relief operations. The system combines human computation and machine learning techniques to process high-volume social media imagery content in real time during natural and human-made disasters. To cope with the noisy nature of the social media imagery data, we use a deep neural network and perceptual hashing techniques to filter out irrelevant and duplicate images. Furthermore, we present a specific use case to assess the severity of infrastructure damage incurred by a disaster. The evaluations of the system on existing disaster datasets as well as a real-world deployment during a recent cyclone prove the effectiveness of the system.]]>
We present an end-to-end social media image processing system called Image4Act. The system aims at collecting, denoising, and classifying imagery content posted on social media platforms to help humanitarian organizations in gaining situational awareness and launching relief operations. The system combines human computation and machine learning techniques to process high-volume social media imagery content in real time during natural and human-made disasters. To cope with the noisy nature of the social media imagery data, we use a deep neural network and perceptual hashing techniques to filter out irrelevant and duplicate images. Furthermore, we present a specific use case to assess the severity of infrastructure damage incurred by a disaster. The evaluations of the system on existing disaster datasets as well as a real-world deployment during a recent cyclone prove the effectiveness of the system.]]>
Tue, 08 Aug 2017 09:48:18 GMT/slideshow/image4act-online-social-media-image-processing-for-disaster-response/78659096mimran15@slideshare.net(mimran15)Image4Act: Online Social Media Image Processing for Disaster Responsemimran15We present an end-to-end social media image processing system called Image4Act. The system aims at collecting, denoising, and classifying imagery content posted on social media platforms to help humanitarian organizations in gaining situational awareness and launching relief operations. The system combines human computation and machine learning techniques to process high-volume social media imagery content in real time during natural and human-made disasters. To cope with the noisy nature of the social media imagery data, we use a deep neural network and perceptual hashing techniques to filter out irrelevant and duplicate images. Furthermore, we present a specific use case to assess the severity of infrastructure damage incurred by a disaster. The evaluations of the system on existing disaster datasets as well as a real-world deployment during a recent cyclone prove the effectiveness of the system.<img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/image4actasonamdemo-170808094818-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> We present an end-to-end social media image processing system called Image4Act. The system aims at collecting, denoising, and classifying imagery content posted on social media platforms to help humanitarian organizations in gaining situational awareness and launching relief operations. The system combines human computation and machine learning techniques to process high-volume social media imagery content in real time during natural and human-made disasters. To cope with the noisy nature of the social media imagery data, we use a deep neural network and perceptual hashing techniques to filter out irrelevant and duplicate images. Furthermore, we present a specific use case to assess the severity of infrastructure damage incurred by a disaster. The evaluations of the system on existing disaster datasets as well as a real-world deployment during a recent cyclone prove the effectiveness of the system.
]]>
5736https://cdn.slidesharecdn.com/ss_thumbnails/image4actasonamdemo-170808094818-thumbnail.jpg?width=120&height=120&fit=boundspresentationBlackhttp://activitystrea.ms/schema/1.0/posthttp://activitystrea.ms/schema/1.0/posted0Real-Time Processing of Social Media Content for Social Good
/slideshow/realtime-processing-of-social-media-content-for-social-good/75705653
imrantutorialhec2017datasciencesocialgood-170505104657 This tutorial was given at the Data Science workshop organized by the Higher Education Commission (HEC) Pakistan in 2017.]]>
This tutorial was given at the Data Science workshop organized by the Higher Education Commission (HEC) Pakistan in 2017.]]>
Fri, 05 May 2017 10:46:57 GMT/slideshow/realtime-processing-of-social-media-content-for-social-good/75705653mimran15@slideshare.net(mimran15)Real-Time Processing of Social Media Content for Social Goodmimran15This tutorial was given at the Data Science workshop organized by the Higher Education Commission (HEC) Pakistan in 2017.<img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/imrantutorialhec2017datasciencesocialgood-170505104657-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> This tutorial was given at the Data Science workshop organized by the Higher Education Commission (HEC) Pakistan in 2017.
]]>
6717https://cdn.slidesharecdn.com/ss_thumbnails/imrantutorialhec2017datasciencesocialgood-170505104657-thumbnail.jpg?width=120&height=120&fit=boundspresentationBlackhttp://activitystrea.ms/schema/1.0/posthttp://activitystrea.ms/schema/1.0/posted0AIDR Tutorial (Artificial Intelligence for Disaster Response)
/slideshow/aidr-tutorial-artificial-intelligence-for-disaster-response/71493798
aidrtutorialforbruceetal-170128164033 This is a short tutorial of AIDR.]]>
This is a short tutorial of AIDR.]]>
Sat, 28 Jan 2017 16:40:33 GMT/slideshow/aidr-tutorial-artificial-intelligence-for-disaster-response/71493798mimran15@slideshare.net(mimran15)AIDR Tutorial (Artificial Intelligence for Disaster Response)mimran15This is a short tutorial of AIDR.<img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/aidrtutorialforbruceetal-170128164033-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> This is a short tutorial of AIDR.
]]>
5356https://cdn.slidesharecdn.com/ss_thumbnails/aidrtutorialforbruceetal-170128164033-thumbnail.jpg?width=120&height=120&fit=boundspresentationBlackhttp://activitystrea.ms/schema/1.0/posthttp://activitystrea.ms/schema/1.0/posted0A Robust Framework for Classifying Evolving Document Streams in an Expert-Machine-Crowd Setting
/slideshow/a-robust-framework-for-classifying-evolving-document-streams-in-an-expertmachinecrowd-setting/70591772
muhammadimranicdm-2016slideshare-170102114317 An emerging challenge in the online classification of social media data streams is to keep the categories used for classification up-to-date. In this paper, we propose an innovative framework based on an Expert-Machine-Crowd (EMC) triad to help categorize items by continuously identifying novel concepts in heterogeneous data streams often riddled with outliers. We unify constrained clustering and outlier detection by formulating a novel optimization problem: COD-Means. We design an algorithm to solve the COD-Means problem and show that COD-Means will not only help detect novel categories but also seamlessly discover human annotation errors and improve the overall quality of the categorization process. Experiments on diverse real data sets demonstrate that our approach is both effective and efficient.]]>
An emerging challenge in the online classification of social media data streams is to keep the categories used for classification up-to-date. In this paper, we propose an innovative framework based on an Expert-Machine-Crowd (EMC) triad to help categorize items by continuously identifying novel concepts in heterogeneous data streams often riddled with outliers. We unify constrained clustering and outlier detection by formulating a novel optimization problem: COD-Means. We design an algorithm to solve the COD-Means problem and show that COD-Means will not only help detect novel categories but also seamlessly discover human annotation errors and improve the overall quality of the categorization process. Experiments on diverse real data sets demonstrate that our approach is both effective and efficient.]]>
Mon, 02 Jan 2017 11:43:17 GMT/slideshow/a-robust-framework-for-classifying-evolving-document-streams-in-an-expertmachinecrowd-setting/70591772mimran15@slideshare.net(mimran15)A Robust Framework for Classifying Evolving Document Streams in an Expert-Machine-Crowd Settingmimran15An emerging challenge in the online classification of social media data streams is to keep the categories used for classification up-to-date. In this paper, we propose an innovative framework based on an Expert-Machine-Crowd (EMC) triad to help categorize items by continuously identifying novel concepts in heterogeneous data streams often riddled with outliers. We unify constrained clustering and outlier detection by formulating a novel optimization problem: COD-Means. We design an algorithm to solve the COD-Means problem and show that COD-Means will not only help detect novel categories but also seamlessly discover human annotation errors and improve the overall quality of the categorization process. Experiments on diverse real data sets demonstrate that our approach is both effective and efficient.<img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/muhammadimranicdm-2016slideshare-170102114317-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> An emerging challenge in the online classification of social media data streams is to keep the categories used for classification up-to-date. In this paper, we propose an innovative framework based on an Expert-Machine-Crowd (EMC) triad to help categorize items by continuously identifying novel concepts in heterogeneous data streams often riddled with outliers. We unify constrained clustering and outlier detection by formulating a novel optimization problem: COD-Means. We design an algorithm to solve the COD-Means problem and show that COD-Means will not only help detect novel categories but also seamlessly discover human annotation errors and improve the overall quality of the categorization process. Experiments on diverse real data sets demonstrate that our approach is both effective and efficient.
]]>
4843https://cdn.slidesharecdn.com/ss_thumbnails/muhammadimranicdm-2016slideshare-170102114317-thumbnail.jpg?width=120&height=120&fit=boundspresentationBlackhttp://activitystrea.ms/schema/1.0/posthttp://activitystrea.ms/schema/1.0/posted0Summarizing Situational Tweets in Crisis Scenario
/slideshow/summarizing-situational-tweets-in-crisis-scenario/65033961
ht2016imranpublished-160816081332 During mass convergence events such as natural disasters, microblogging platforms like Twitter are widely used by affected people to post situational awareness messages. These crisis related messages disperse among multiple categories like infrastructure damage, information about missing, injured, and dead people etc. The challenge here is to extract important situational updates from these messages, assign them appropriate informational categories, and finally summarize big trove of information in each category. In this paper, we propose a novel framework which first assigns tweets into different situational classes and then summarize those tweets. In the summarization phase, we propose a two stage summarization framework which first extracts a set of important tweets from the whole set of information through an Integer-linear programming (ILP) based optimization technique and then follows a word graph and content word based abstractive summarization technique to produce the final summary. Our method is time and memory efficient and outperforms the baseline in terms of quality, coverage of events, locations et al., effectiveness, and utility in disaster scenarios.]]>
During mass convergence events such as natural disasters, microblogging platforms like Twitter are widely used by affected people to post situational awareness messages. These crisis related messages disperse among multiple categories like infrastructure damage, information about missing, injured, and dead people etc. The challenge here is to extract important situational updates from these messages, assign them appropriate informational categories, and finally summarize big trove of information in each category. In this paper, we propose a novel framework which first assigns tweets into different situational classes and then summarize those tweets. In the summarization phase, we propose a two stage summarization framework which first extracts a set of important tweets from the whole set of information through an Integer-linear programming (ILP) based optimization technique and then follows a word graph and content word based abstractive summarization technique to produce the final summary. Our method is time and memory efficient and outperforms the baseline in terms of quality, coverage of events, locations et al., effectiveness, and utility in disaster scenarios.]]>
Tue, 16 Aug 2016 08:13:32 GMT/slideshow/summarizing-situational-tweets-in-crisis-scenario/65033961mimran15@slideshare.net(mimran15)Summarizing Situational Tweets in Crisis Scenariomimran15During mass convergence events such as natural disasters, microblogging platforms like Twitter are widely used by affected people to post situational awareness messages. These crisis related messages disperse among multiple categories like infrastructure damage, information about missing, injured, and dead people etc. The challenge here is to extract important situational updates from these messages, assign them appropriate informational categories, and finally summarize big trove of information in each category. In this paper, we propose a novel framework which first assigns tweets into different situational classes and then summarize those tweets. In the summarization phase, we propose a two stage summarization framework which first extracts a set of important tweets from the whole set of information through an Integer-linear programming (ILP) based optimization technique and then follows a word graph and content word based abstractive summarization technique to produce the final summary. Our method is time and memory efficient and outperforms the baseline in terms of quality, coverage of events, locations et al., effectiveness, and utility in disaster scenarios.<img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/ht2016imranpublished-160816081332-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> During mass convergence events such as natural disasters, microblogging platforms like Twitter are widely used by affected people to post situational awareness messages. These crisis related messages disperse among multiple categories like infrastructure damage, information about missing, injured, and dead people etc. The challenge here is to extract important situational updates from these messages, assign them appropriate informational categories, and finally summarize big trove of information in each category. In this paper, we propose a novel framework which first assigns tweets into different situational classes and then summarize those tweets. In the summarization phase, we propose a two stage summarization framework which first extracts a set of important tweets from the whole set of information through an Integer-linear programming (ILP) based optimization technique and then follows a word graph and content word based abstractive summarization technique to produce the final summary. Our method is time and memory efficient and outperforms the baseline in terms of quality, coverage of events, locations et al., effectiveness, and utility in disaster scenarios.
]]>
6264https://cdn.slidesharecdn.com/ss_thumbnails/ht2016imranpublished-160816081332-thumbnail.jpg?width=120&height=120&fit=boundspresentationBlackhttp://activitystrea.ms/schema/1.0/posthttp://activitystrea.ms/schema/1.0/posted0The Role of Social Media and Artificial Intelligence for Disaster Response
/slideshow/the-role-of-social-media-and-artificial-intelligence-for-disaster-response/62494105
imrankeynoteiscram2016final-160528135159 Keynote slides for ISCRAM 2016.
"Social Media platforms such as Twitter are invaluable sources of time-critical information. Information on social media communicated during emergencies convey timely and actionable information. For rapid crisis response, real-time insights are important for emergency responders. Although, many humanitarian organizations would like to use this information, however they struggle due a number of issues such as information overload, information vagueness, less credible and misinformation. In this talk, I will describe the role of social media and potential artificial intelligence computational techniques useful for humanitarian organizations and decision makers to make sense of social media data for rapid crisis response."]]>
Keynote slides for ISCRAM 2016.
"Social Media platforms such as Twitter are invaluable sources of time-critical information. Information on social media communicated during emergencies convey timely and actionable information. For rapid crisis response, real-time insights are important for emergency responders. Although, many humanitarian organizations would like to use this information, however they struggle due a number of issues such as information overload, information vagueness, less credible and misinformation. In this talk, I will describe the role of social media and potential artificial intelligence computational techniques useful for humanitarian organizations and decision makers to make sense of social media data for rapid crisis response."]]>
Sat, 28 May 2016 13:51:59 GMT/slideshow/the-role-of-social-media-and-artificial-intelligence-for-disaster-response/62494105mimran15@slideshare.net(mimran15)The Role of Social Media and Artificial Intelligence for Disaster Responsemimran15Keynote slides for ISCRAM 2016.
"Social Media platforms such as Twitter are invaluable sources of time-critical information. Information on social media communicated during emergencies convey timely and actionable information. For rapid crisis response, real-time insights are important for emergency responders. Although, many humanitarian organizations would like to use this information, however they struggle due a number of issues such as information overload, information vagueness, less credible and misinformation. In this talk, I will describe the role of social media and potential artificial intelligence computational techniques useful for humanitarian organizations and decision makers to make sense of social media data for rapid crisis response."<img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/imrankeynoteiscram2016final-160528135159-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> Keynote slides for ISCRAM 2016.
"Social Media platforms such as Twitter are invaluable sources of time-critical information. Information on social media communicated during emergencies convey timely and actionable information. For rapid crisis response, real-time insights are important for emergency responders. Although, many humanitarian organizations would like to use this information, however they struggle due a number of issues such as information overload, information vagueness, less credible and misinformation. In this talk, I will describe the role of social media and potential artificial intelligence computational techniques useful for humanitarian organizations and decision makers to make sense of social media data for rapid crisis response."
]]>
725216https://cdn.slidesharecdn.com/ss_thumbnails/imrankeynoteiscram2016final-160528135159-thumbnail.jpg?width=120&height=120&fit=boundspresentation000000http://activitystrea.ms/schema/1.0/posthttp://activitystrea.ms/schema/1.0/posted0Introduction to Machine Learning: An Application to Disaster Response
/slideshow/introduction-to-machine-learning-an-application-to-disaster-response/55237623
mlaidrqstp-151118060041-lva1-app6891 Introduction to Machine Learning talk (part-2) focused on the applications of machine learning in the disaster response domain. In the first part of the talk, we presented different machine learning approaches.]]>
Introduction to Machine Learning talk (part-2) focused on the applications of machine learning in the disaster response domain. In the first part of the talk, we presented different machine learning approaches.]]>
Wed, 18 Nov 2015 06:00:40 GMT/slideshow/introduction-to-machine-learning-an-application-to-disaster-response/55237623mimran15@slideshare.net(mimran15)Introduction to Machine Learning: An Application to Disaster Responsemimran15Introduction to Machine Learning talk (part-2) focused on the applications of machine learning in the disaster response domain. In the first part of the talk, we presented different machine learning approaches.<img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/mlaidrqstp-151118060041-lva1-app6891-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> Introduction to Machine Learning talk (part-2) focused on the applications of machine learning in the disaster response domain. In the first part of the talk, we presented different machine learning approaches.
]]>
9247https://cdn.slidesharecdn.com/ss_thumbnails/mlaidrqstp-151118060041-lva1-app6891-thumbnail.jpg?width=120&height=120&fit=boundspresentationBlackhttp://activitystrea.ms/schema/1.0/posthttp://activitystrea.ms/schema/1.0/posted0Artificial Intelligence for Disaster Response
/slideshow/artificial-intelligence-for-disaster-response/48397128
aidr-www14-150520172537-lva1-app6891 We present AIDR (Artificial Intelligence for Disaster Response), a platform designed to perform automatic classification of crisis-related microblog communications. AIDR enables humans and machines to work together to apply human intelligence to large-scale data at high speed. The objective of AIDR is to classify messages that people
post during disasters into a set of user-defined categories of information (e.g., 鈥渘eeds鈥�, 鈥渄amage鈥�, etc.) For this purpose, the system continuously ingests data from Twitter, processes it (i.e., using machine learning classification techniques) and leverages human-participation (through crowdsourcing) in real-time. AIDR has been successfully tested to classify informative vs. non-informative tweets posted during the 2013 Pakistan Earthquake. Overall, we achieved a classification quality (measured using AUC) of 80%. AIDR is available at http://aidr.qcri.org/.]]>
We present AIDR (Artificial Intelligence for Disaster Response), a platform designed to perform automatic classification of crisis-related microblog communications. AIDR enables humans and machines to work together to apply human intelligence to large-scale data at high speed. The objective of AIDR is to classify messages that people
post during disasters into a set of user-defined categories of information (e.g., 鈥渘eeds鈥�, 鈥渄amage鈥�, etc.) For this purpose, the system continuously ingests data from Twitter, processes it (i.e., using machine learning classification techniques) and leverages human-participation (through crowdsourcing) in real-time. AIDR has been successfully tested to classify informative vs. non-informative tweets posted during the 2013 Pakistan Earthquake. Overall, we achieved a classification quality (measured using AUC) of 80%. AIDR is available at http://aidr.qcri.org/.]]>
Wed, 20 May 2015 17:25:37 GMT/slideshow/artificial-intelligence-for-disaster-response/48397128mimran15@slideshare.net(mimran15)Artificial Intelligence for Disaster Responsemimran15We present AIDR (Artificial Intelligence for Disaster Response), a platform designed to perform automatic classification of crisis-related microblog communications. AIDR enables humans and machines to work together to apply human intelligence to large-scale data at high speed. The objective of AIDR is to classify messages that people
post during disasters into a set of user-defined categories of information (e.g., 鈥渘eeds鈥�, 鈥渄amage鈥�, etc.) For this purpose, the system continuously ingests data from Twitter, processes it (i.e., using machine learning classification techniques) and leverages human-participation (through crowdsourcing) in real-time. AIDR has been successfully tested to classify informative vs. non-informative tweets posted during the 2013 Pakistan Earthquake. Overall, we achieved a classification quality (measured using AUC) of 80%. AIDR is available at http://aidr.qcri.org/.<img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/aidr-www14-150520172537-lva1-app6891-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> We present AIDR (Artificial Intelligence for Disaster Response), a platform designed to perform automatic classification of crisis-related microblog communications. AIDR enables humans and machines to work together to apply human intelligence to large-scale data at high speed. The objective of AIDR is to classify messages that people
post during disasters into a set of user-defined categories of information (e.g., 鈥渘eeds鈥�, 鈥渄amage鈥�, etc.) For this purpose, the system continuously ingests data from Twitter, processes it (i.e., using machine learning classification techniques) and leverages human-participation (through crowdsourcing) in real-time. AIDR has been successfully tested to classify informative vs. non-informative tweets posted during the 2013 Pakistan Earthquake. Overall, we achieved a classification quality (measured using AUC) of 80%. AIDR is available at http://aidr.qcri.org/.
]]>
36103https://cdn.slidesharecdn.com/ss_thumbnails/aidr-www14-150520172537-lva1-app6891-thumbnail.jpg?width=120&height=120&fit=boundspresentation000000http://activitystrea.ms/schema/1.0/posthttp://activitystrea.ms/schema/1.0/posted0A Real-time Heuristic-based Unsupervised Method for Name Disambiguation in Digital Libraries
/mimran15/a-realtime-heuristicbased-unsupervised-method-for-name-disambiguation-in-digital-libraries
imran-wosp-ndsm-140920050828-phpapp02 This paper addresses the baffling problem of name disam- biguation in the context of digital libraries that administer bibliographic citations. The problem emanates when multi- ple authors share a common name or when multiple name variations of an author appear in citation records. Name dis- ambiguation is not trivial to solve, and most of the digital libraries do not provide an efficient way to accurately iden- tify the citation records of an author. Furthermore, lack of complete meta-data information in digital libraries hinders the existence of generic algorithm that can be applicable on any dataset. We propose a heuristic-based, unsupervised and adaptive method that also embraces users鈥� interaction to count users鈥� feedback in disambiguation process. Moreover, the method exploits important features associated with an author and citation records such as co-authors, affiliation, publication title, venue etc., and contrives a conspicuous multilayer hierarchical clustering algorithm, which tunes it- self according to the available information and form clusters of unambiguous records. Our experiments on a set of re- searchers that are contemplated to be highly ambiguous de- cisively produced high precision and recall results and affirm the viability of our algorithm.]]>
This paper addresses the baffling problem of name disam- biguation in the context of digital libraries that administer bibliographic citations. The problem emanates when multi- ple authors share a common name or when multiple name variations of an author appear in citation records. Name dis- ambiguation is not trivial to solve, and most of the digital libraries do not provide an efficient way to accurately iden- tify the citation records of an author. Furthermore, lack of complete meta-data information in digital libraries hinders the existence of generic algorithm that can be applicable on any dataset. We propose a heuristic-based, unsupervised and adaptive method that also embraces users鈥� interaction to count users鈥� feedback in disambiguation process. Moreover, the method exploits important features associated with an author and citation records such as co-authors, affiliation, publication title, venue etc., and contrives a conspicuous multilayer hierarchical clustering algorithm, which tunes it- self according to the available information and form clusters of unambiguous records. Our experiments on a set of re- searchers that are contemplated to be highly ambiguous de- cisively produced high precision and recall results and affirm the viability of our algorithm.]]>
Sat, 20 Sep 2014 05:08:28 GMT/mimran15/a-realtime-heuristicbased-unsupervised-method-for-name-disambiguation-in-digital-librariesmimran15@slideshare.net(mimran15)A Real-time Heuristic-based Unsupervised Method for Name Disambiguation in Digital Librariesmimran15This paper addresses the baffling problem of name disam- biguation in the context of digital libraries that administer bibliographic citations. The problem emanates when multi- ple authors share a common name or when multiple name variations of an author appear in citation records. Name dis- ambiguation is not trivial to solve, and most of the digital libraries do not provide an efficient way to accurately iden- tify the citation records of an author. Furthermore, lack of complete meta-data information in digital libraries hinders the existence of generic algorithm that can be applicable on any dataset. We propose a heuristic-based, unsupervised and adaptive method that also embraces users鈥� interaction to count users鈥� feedback in disambiguation process. Moreover, the method exploits important features associated with an author and citation records such as co-authors, affiliation, publication title, venue etc., and contrives a conspicuous multilayer hierarchical clustering algorithm, which tunes it- self according to the available information and form clusters of unambiguous records. Our experiments on a set of re- searchers that are contemplated to be highly ambiguous de- cisively produced high precision and recall results and affirm the viability of our algorithm.<img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/imran-wosp-ndsm-140920050828-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> This paper addresses the baffling problem of name disam- biguation in the context of digital libraries that administer bibliographic citations. The problem emanates when multi- ple authors share a common name or when multiple name variations of an author appear in citation records. Name dis- ambiguation is not trivial to solve, and most of the digital libraries do not provide an efficient way to accurately iden- tify the citation records of an author. Furthermore, lack of complete meta-data information in digital libraries hinders the existence of generic algorithm that can be applicable on any dataset. We propose a heuristic-based, unsupervised and adaptive method that also embraces users鈥� interaction to count users鈥� feedback in disambiguation process. Moreover, the method exploits important features associated with an author and citation records such as co-authors, affiliation, publication title, venue etc., and contrives a conspicuous multilayer hierarchical clustering algorithm, which tunes it- self according to the available information and form clusters of unambiguous records. Our experiments on a set of re- searchers that are contemplated to be highly ambiguous de- cisively produced high precision and recall results and affirm the viability of our algorithm.
]]>
11922https://cdn.slidesharecdn.com/ss_thumbnails/imran-wosp-ndsm-140920050828-phpapp02-thumbnail.jpg?width=120&height=120&fit=boundspresentationBlackhttp://activitystrea.ms/schema/1.0/posthttp://activitystrea.ms/schema/1.0/posted0Coordinating Human and Machine Intelligence to Classify Microblog Communica0ons in Crises
/slideshow/iscram14-imran-2/34964254
iscram14imran2-140521130037-phpapp02 An emerging paradigm for the processing of data streams involves human and machine computation working together, allowing human intelligence to process large-scale data. We apply this approach to the classification of crisis-related messages in microblog streams. We begin by describing the platform AIDR (Artificial Intelligence for Disaster Response), which collects human annotations over time to create and maintain automatic supervised classifiers for social media messages. Next, we study two significant challenges in its design: (1) identifying which elements must be labeled by humans, and (2) determining when to ask for such annotations to be done. The first challenge is selecting the items to be labeled by crowdsourcing workers to maximize the productivity of their work. The second challenge is to schedule the work in order to reliably maintain high classification accuracy over time. We provide and validate answers to these challenges by extensive experimentation on real- world datasets.]]>
An emerging paradigm for the processing of data streams involves human and machine computation working together, allowing human intelligence to process large-scale data. We apply this approach to the classification of crisis-related messages in microblog streams. We begin by describing the platform AIDR (Artificial Intelligence for Disaster Response), which collects human annotations over time to create and maintain automatic supervised classifiers for social media messages. Next, we study two significant challenges in its design: (1) identifying which elements must be labeled by humans, and (2) determining when to ask for such annotations to be done. The first challenge is selecting the items to be labeled by crowdsourcing workers to maximize the productivity of their work. The second challenge is to schedule the work in order to reliably maintain high classification accuracy over time. We provide and validate answers to these challenges by extensive experimentation on real- world datasets.]]>
Wed, 21 May 2014 13:00:37 GMT/slideshow/iscram14-imran-2/34964254mimran15@slideshare.net(mimran15)Coordinating Human and Machine Intelligence to Classify Microblog Communica0ons in Crisesmimran15An emerging paradigm for the processing of data streams involves human and machine computation working together, allowing human intelligence to process large-scale data. We apply this approach to the classification of crisis-related messages in microblog streams. We begin by describing the platform AIDR (Artificial Intelligence for Disaster Response), which collects human annotations over time to create and maintain automatic supervised classifiers for social media messages. Next, we study two significant challenges in its design: (1) identifying which elements must be labeled by humans, and (2) determining when to ask for such annotations to be done. The first challenge is selecting the items to be labeled by crowdsourcing workers to maximize the productivity of their work. The second challenge is to schedule the work in order to reliably maintain high classification accuracy over time. We provide and validate answers to these challenges by extensive experimentation on real- world datasets.<img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/iscram14imran2-140521130037-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> An emerging paradigm for the processing of data streams involves human and machine computation working together, allowing human intelligence to process large-scale data. We apply this approach to the classification of crisis-related messages in microblog streams. We begin by describing the platform AIDR (Artificial Intelligence for Disaster Response), which collects human annotations over time to create and maintain automatic supervised classifiers for social media messages. Next, we study two significant challenges in its design: (1) identifying which elements must be labeled by humans, and (2) determining when to ask for such annotations to be done. The first challenge is selecting the items to be labeled by crowdsourcing workers to maximize the productivity of their work. The second challenge is to schedule the work in order to reliably maintain high classification accuracy over time. We provide and validate answers to these challenges by extensive experimentation on real- world datasets.
]]>
12665https://cdn.slidesharecdn.com/ss_thumbnails/iscram14imran2-140521130037-phpapp02-thumbnail.jpg?width=120&height=120&fit=boundspresentationBlackhttp://activitystrea.ms/schema/1.0/posthttp://activitystrea.ms/schema/1.0/posted0Tweet4act: Using Incident-Specific Profiles for Classifying Crisis-Related Messages
/slideshow/tweet4act-using-incidentspecific-profiles-for-classifying-crisisrelated-messages/25306445
imran-tweet4act-iscram2013-130816055946-phpapp01 This work describes our work presented at the ISCRAM-2013 conference. We presented Tweet4act system, which is used to detect and classify crisis-related messages communicated over a microblogging platform. Our system relies on extracting content features from each message. These features and the use of an incident-specific dictionary allow us to determine the period type of an incident that each message belongs to. ]]>
This work describes our work presented at the ISCRAM-2013 conference. We presented Tweet4act system, which is used to detect and classify crisis-related messages communicated over a microblogging platform. Our system relies on extracting content features from each message. These features and the use of an incident-specific dictionary allow us to determine the period type of an incident that each message belongs to. ]]>
Fri, 16 Aug 2013 05:59:46 GMT/slideshow/tweet4act-using-incidentspecific-profiles-for-classifying-crisisrelated-messages/25306445mimran15@slideshare.net(mimran15)Tweet4act: Using Incident-Specific Profiles for Classifying Crisis-Related Messagesmimran15This work describes our work presented at the ISCRAM-2013 conference. We presented Tweet4act system, which is used to detect and classify crisis-related messages communicated over a microblogging platform. Our system relies on extracting content features from each message. These features and the use of an incident-specific dictionary allow us to determine the period type of an incident that each message belongs to. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/imran-tweet4act-iscram2013-130816055946-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> This work describes our work presented at the ISCRAM-2013 conference. We presented Tweet4act system, which is used to detect and classify crisis-related messages communicated over a microblogging platform. Our system relies on extracting content features from each message. These features and the use of an incident-specific dictionary allow us to determine the period type of an incident that each message belongs to.
]]>
11743https://cdn.slidesharecdn.com/ss_thumbnails/imran-tweet4act-iscram2013-130816055946-phpapp01-thumbnail.jpg?width=120&height=120&fit=boundspresentationBlackhttp://activitystrea.ms/schema/1.0/posthttp://activitystrea.ms/schema/1.0/posted0Extracting Information Nuggets from Disaster-Related Messages in Social Media
/mimran15/imran-iscramnuggest
imran-iscram-nuggest-130514073723-phpapp02 This presentation describes our work presented at the 10th International Conference on Information Systems on Crisis Response and Management (ISCRAM) in Baden-Baden, Germany. The work shows the importance of microblogging websites such as Twitter, and huge number of informative messages that can contribute to situational awareness at the time of disasters. Specifically, the work shows the classification, and information extractions of those valuable, actionable informative messages that people post during emergencies. ]]>
This presentation describes our work presented at the 10th International Conference on Information Systems on Crisis Response and Management (ISCRAM) in Baden-Baden, Germany. The work shows the importance of microblogging websites such as Twitter, and huge number of informative messages that can contribute to situational awareness at the time of disasters. Specifically, the work shows the classification, and information extractions of those valuable, actionable informative messages that people post during emergencies. ]]>
Tue, 14 May 2013 07:37:23 GMT/mimran15/imran-iscramnuggestmimran15@slideshare.net(mimran15)Extracting Information Nuggets from Disaster-Related Messages in Social Mediamimran15This presentation describes our work presented at the 10th International Conference on Information Systems on Crisis Response and Management (ISCRAM) in Baden-Baden, Germany. The work shows the importance of microblogging websites such as Twitter, and huge number of informative messages that can contribute to situational awareness at the time of disasters. Specifically, the work shows the classification, and information extractions of those valuable, actionable informative messages that people post during emergencies. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/imran-iscram-nuggest-130514073723-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> This presentation describes our work presented at the 10th International Conference on Information Systems on Crisis Response and Management (ISCRAM) in Baden-Baden, Germany. The work shows the importance of microblogging websites such as Twitter, and huge number of informative messages that can contribute to situational awareness at the time of disasters. Specifically, the work shows the classification, and information extractions of those valuable, actionable informative messages that people post during emergencies.
]]>
10441https://cdn.slidesharecdn.com/ss_thumbnails/mashupsthatspeakthelanguageoftheusers-110526082541-phpapp02-thumbnail.jpg?width=120&height=120&fit=boundspresentationBlackhttp://activitystrea.ms/schema/1.0/posthttp://activitystrea.ms/schema/1.0/posted0Reseval Mashup Platform Talk at SECO
/slideshow/reseval-mahup-plateform-talk-at-seco/5196323
resevalpresentationwithmashupsecotalk-100914034439-phpapp02 We are going to represent a Mashup platform for the research evaluation. This talk was given at 2nd Search computing workshop in Como, italy on 27-may-2010.]]>
We are going to represent a Mashup platform for the research evaluation. This talk was given at 2nd Search computing workshop in Como, italy on 27-may-2010.]]>
Tue, 14 Sep 2010 03:44:22 GMT/slideshow/reseval-mahup-plateform-talk-at-seco/5196323mimran15@slideshare.net(mimran15)Reseval Mashup Platform Talk at SECOmimran15We are going to represent a Mashup platform for the research evaluation. This talk was given at 2nd Search computing workshop in Como, italy on 27-may-2010.<img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/resevalpresentationwithmashupsecotalk-100914034439-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> We are going to represent a Mashup platform for the research evaluation. This talk was given at 2nd Search computing workshop in Como, italy on 27-may-2010.
]]>
7925https://cdn.slidesharecdn.com/ss_thumbnails/resevalpresentation-100316143518-phpapp01-thumbnail.jpg?width=120&height=120&fit=boundspresentationBlackhttp://activitystrea.ms/schema/1.0/posthttp://activitystrea.ms/schema/1.0/posted0https://cdn.slidesharecdn.com/profile-photo-mimran15-48x48.jpg?cb=1672476538Understanding the role of Social Media during mass convergence events by using big data analysis techniques such as text classification, data mining, and interactive machine learning.mimran.mehttps://cdn.slidesharecdn.com/ss_thumbnails/final2www18surveypaper-180425125551-thumbnail.jpg?width=320&height=320&fit=boundsslideshow/processing-social-media-messages-in-mass-emergency-a-survey-94984592/94984592Processing Social Medi...https://cdn.slidesharecdn.com/ss_thumbnails/fullpaperdamageassessment-170808192839-thumbnail.jpg?width=320&height=320&fit=boundsslideshow/damage-assessment-from-social-media-imagery-data-during-disasters/78675870Damage Assessment from...https://cdn.slidesharecdn.com/ss_thumbnails/image4actasonamdemo-170808094818-thumbnail.jpg?width=320&height=320&fit=boundsslideshow/image4act-online-social-media-image-processing-for-disaster-response/78659096Image4Act: Online Soci...