Public expects a prompt response from online services, including emergency response organizations to requests for help posted on social media. However, the information overload experienced by these organizations, coupled with their limited human resources, challenges them to timely identifying and prioritizing such requests. We present a novel model to formally characterize social media requests and then, develop a Learning-to-Rank system using this model.
Paper: Purohit, H., Castillo, C., Imran, M., and Pandey, R. (2018). Social-EOC: Serviceability Model To Rank Social Media Requests for Emergency Operation Centers. ASONAM 2018.
Social Media & Web Mining for Public Services of Smart Cities - SSA TalkHemant Purohit
This talk at Data Science Seminar of SSA presents challenges and methods to model behavior on social media & Web for application opportunities for public services. The talk also demonstrates an in-depth case study of mining intentional behavior from the noisy natural language text of social media messages during disasters and how it could assist emergency services of future smart cities.
Given the growth of social media and rapid evolution of Web of Data, we have unprecedented opportunities to improve crisis response by extracting social signals, creating spatio-temporal mappings, performing analytics on social and Web of Data, and supporting a variety of applications. Such applications can help provide situational awareness during an emergency, improve preparedness, and assist during the rebuilding/recovery phase of a disaster. Data mining can provide valuable insights to support emergency responders and other stakeholders during crisis. However, there are a number of challenges and existing computing technology may not work in all cases. Therefore, our objective here is to present the characterization of such data mining tasks, and challenges that need further research attention for leveraging social media and Web of Data to assist crisis response coordination.
Ignite talk at ICCM-2013 at United Nations (UN) Nairobi by NSF SoCS project researcher, Hemant Purohit - 'How to Leverage Social Media Communities for Crisis Response Coordination' using Human+Machine computing
Key-message: We need to extract smart actionable data out of big crisis data to assist response coordination, by focusing on demand-supply centric technology.
More at Kno.e.sis' SOCS project page: http://knoesis.org/research/semsoc/projects/socs
Also, Crisis Informatics at Kno.e.sis: http://j.mp/CrisisRes
Workload-bound Ranking of Alerts for Emergency Operation Centers - Web Intell...Hemant Purohit
This research presents a novel problem and a model to quantify the relationship between the performance metrics of automated ranking systems (e.g., recall, NDCG) and the bounds on the human performance (e.g., cognitive workload) in emergency services. We synthesize an alert-based ranking system that enforces these bounds to avoid overwhelming end-users for achieving the Human-AI collaboration.
Citation:
Purohit, H., Castillo, C., Imran, M., & Pandey, R. (2018). Ranking of Social Media Alerts with Workload Bounds in Emergency Operation Centers. IEEE/WIC/ACM Web-Intelligence. ArXiv preprint: https://arxiv.org/abs/1809.08489
Public Health Crisis Analytics for Gender ViolenceHemant Purohit
Research-progress talk on the use of data analytics methods for one of the major public health crisis in the world Gender-based Violence and the campaign engagement in the initiatives of Non-profit organizations.
Invited talk presented by Hemant Purohit (http://knoesis.org/researchers/hemant) at the NCSU workshop on IT for sustainable tourism development. The talk presents application of technology developed for crisis coordination into more general marketplace coordination via social media for helping suppliers (micro-entrepreneurs) and demanders (tourists).
User Classification of Organization and Organization Affiliated Users during ...Hemant Purohit
Understanding who participates and for what activities in social media conversations after crisis events can be helpful for response coordination agencies, especially other organizations, and their affiliates. Check paper at:
Hemant Purohit, & Jennifer Chan. (2017). Classifying User Types on Social Media to inform Who-What-Where Coordination during Crisis Response. In ISCRAM-17.
Social Media & Web Mining for Public Services of Smart Cities - SSA TalkHemant Purohit
This talk at Data Science Seminar of SSA presents challenges and methods to model behavior on social media & Web for application opportunities for public services. The talk also demonstrates an in-depth case study of mining intentional behavior from the noisy natural language text of social media messages during disasters and how it could assist emergency services of future smart cities.
Given the growth of social media and rapid evolution of Web of Data, we have unprecedented opportunities to improve crisis response by extracting social signals, creating spatio-temporal mappings, performing analytics on social and Web of Data, and supporting a variety of applications. Such applications can help provide situational awareness during an emergency, improve preparedness, and assist during the rebuilding/recovery phase of a disaster. Data mining can provide valuable insights to support emergency responders and other stakeholders during crisis. However, there are a number of challenges and existing computing technology may not work in all cases. Therefore, our objective here is to present the characterization of such data mining tasks, and challenges that need further research attention for leveraging social media and Web of Data to assist crisis response coordination.
Ignite talk at ICCM-2013 at United Nations (UN) Nairobi by NSF SoCS project researcher, Hemant Purohit - 'How to Leverage Social Media Communities for Crisis Response Coordination' using Human+Machine computing
Key-message: We need to extract smart actionable data out of big crisis data to assist response coordination, by focusing on demand-supply centric technology.
More at Kno.e.sis' SOCS project page: http://knoesis.org/research/semsoc/projects/socs
Also, Crisis Informatics at Kno.e.sis: http://j.mp/CrisisRes
Workload-bound Ranking of Alerts for Emergency Operation Centers - Web Intell...Hemant Purohit
This research presents a novel problem and a model to quantify the relationship between the performance metrics of automated ranking systems (e.g., recall, NDCG) and the bounds on the human performance (e.g., cognitive workload) in emergency services. We synthesize an alert-based ranking system that enforces these bounds to avoid overwhelming end-users for achieving the Human-AI collaboration.
Citation:
Purohit, H., Castillo, C., Imran, M., & Pandey, R. (2018). Ranking of Social Media Alerts with Workload Bounds in Emergency Operation Centers. IEEE/WIC/ACM Web-Intelligence. ArXiv preprint: https://arxiv.org/abs/1809.08489
Public Health Crisis Analytics for Gender ViolenceHemant Purohit
Research-progress talk on the use of data analytics methods for one of the major public health crisis in the world Gender-based Violence and the campaign engagement in the initiatives of Non-profit organizations.
Invited talk presented by Hemant Purohit (http://knoesis.org/researchers/hemant) at the NCSU workshop on IT for sustainable tourism development. The talk presents application of technology developed for crisis coordination into more general marketplace coordination via social media for helping suppliers (micro-entrepreneurs) and demanders (tourists).
User Classification of Organization and Organization Affiliated Users during ...Hemant Purohit
Understanding who participates and for what activities in social media conversations after crisis events can be helpful for response coordination agencies, especially other organizations, and their affiliates. Check paper at:
Hemant Purohit, & Jennifer Chan. (2017). Classifying User Types on Social Media to inform Who-What-Where Coordination during Crisis Response. In ISCRAM-17.
Social Media, Crisis Communication and Emergency Management: Leveraging Web 2...Connie White
Detailing guidelines and safe practices for using social media across a range of emergency management applications‚ Social Media, Crisis Communication, and Emergency Management: Leveraging Web 2.0 Technologies supplies cutting-edge methods to help you inform the public‚ reduce information overload‚ and ultimately‚ save more lives.
Introduces collaborative mapping tools that can be customized to your needs
Explores free and open-source disaster management systems‚ such as Sahana and Ushahidi
Covers freely available social media technologies—including Facebook‚ Twitter‚ and YouTube
Untapped Potential: Evaluating State Emergency Management Agency Web Sites 2...Dawn Dawson
The 2007-8 Study and Survey that sparked my interest in SMEM and passion for Preparedness & Public Safety . It was clear to me that communicating virtually through various platforms would open communication to the public and could reduce if not eliminate injuries/fatalities. Analysis began in Jan-March, survey in May, myself as Marketing Coordinator C.E.R.T. for the City of Independence/Eastern Jackson County EJC/EOC Fire Station #1 Independence, Mo joined Twitter to show my EM how it could be used on 13 June 2008 . . .
Department of Homeland Security Report- Lessons Learned Using Social Media Du...Mark Rybchuk
What did local governments learn about using social media during a crisis and how did it help serve residents during an emergency? HootSuite Enterprise is referenced on page 33 as one of the key assets the City of New York used during this emergency.
Lessons learned from Social media intervention during hurricane SandyPrayukth K V
Social media and collaborative technologies have become critical components of emergency preparedness, response, and recovery. From the international response efforts in major tsunamis to hurricane response and recovery in major U.S. cities, many government officials now turn to social media technologies to share information and connect with citizens during all phases of a crisis. Implementing these new technologies, however, requires that responding agencies adopt new communication strategies and engagement methods.
Traffic Gridlock: A Bad, Mis-Leading Metaphor that Makes for Bad, Mis-Directe...Barry Wellar
In a previous publication, Traffic Gridlock: The Real Deal or a Pile of Nonsense?, I reported on a study which applied several research procedures to examine media stories and Google search items containing the terms “traffic gridlock” or “gridlock” implying traffic gridlock. The objective was to ascertain whether the media stories and Google items establish that traffic gridlock is a real deal matter, or whether the stories and items contribute to a pile of nonsense. The finding was that 99% of the stories and items belong in the nonsense pile.
And therein lies a puzzle: How is it that “traffic gridlock” enjoys considerable media and Google popularity, but little to no evidence demonstrating the occurrence of “traffic gridlock” accompanies the vast majority of stories and Google entries? In this report I explore one possible explanation, and the associated implication for public policy. That is, traffic gridlock” is a bad, mis-leading metaphor which has been accepted and promulgated by some parties as a truth for which no proof exists and none is needed. And, the associated cause-effect relationship that I comment on is that a bad, mis-leading metaphor is a bad, mis-directed basis for setting public policy.
To support this explanation I introduce the good metaphor “traffic blockage”, and use it as a means to discredit and dismiss the traffic gridlock metaphor which I believe erroneously distorts understanding the role of motor vehicle congestion in urban places, and obscures/confounds the appropriate ways and means of considering and addressing urban motor vehicle congestion. And, as per the initial paper, an invitation is extended to anyone who has traffic gridlock evidence: please call it to my attention at the earliest so that I can adjust my thinking and revise my papers.
Abstract: The wisdom of the crowd is a well-known example of collective intelligence, wherein an aggregated judgment of a group of individuals is superior to that of an individual. The aggregated judgment is surprisingly accurate to predict the outcome of a range of events from geopolitical forecasting to stock price index. Recent research studies have shown that participants’ previous performance data contributes to the identification of a subset of participants that can collectively predict an accurate outcome. In the absence of such performance data, researchers have explored the role of human-perceived diversity to assemble an intelligent crowd. Online social networks are becoming increasingly popular in sharing and seeking domain-specific knowledge. Tapping the crowd wisdom on online social networks can help prediction for several real-world tasks. Independent and contextually diverse crowd selection using social media data imposes unique challenges such as,
Complementing short and potentially noisy social media data with domain specific knowledge.
Lack of labeled data in evaluating closely connected social media participants.
Combining social media text, indicating a diverse perspective, and network features, indicating potential influence, in diverse crowd selection.
Interpretable diversity measure to understand the type of diversity that can enhance the performance of a crowd.
This dissertation first provides several data-driven measures from social-media data and shows that participant diversity can be inferred from social media data and that it can benefit performance in the real world prediction tasks. Domain-specific knowledge graphs provide the foundational basis to evaluate and drive contextually diverse crowd selection and complementing short social media text. Novel group detection and crowd selection algorithms incorporating text, network, and knowledge-graph can automatically select a diverse crowd and also provide recognizable diversity interpretation. It is shown that such a diverse crowd can accurately predict the outcome of real-world events. These results have implications for numerous domains that utilize aggregated judgments - from consumer reviews to econometrics, to geopolitical forecasting and intelligence analysis.
Video: https://youtu.be/KCtoP5u5IqY
Album: https://www.facebook.com/pg/Kno.e.sis/photos/?tab=album&album_id=2538081172893382
Main topics: social media mining, social networks, and influence propagation. Includes an application to social media in disasters.
Talk given at the European Summer School on Information Retrieval (ESSIR 2015) on September 1st, 2015.
See also: http://chato.cl/
Social media? It's serious! Understanding the dark side of social mediaIan McCarthy
Research and practice have mostly focused on the “bright side” of social media, aiming to understand and help in leveraging the manifold opportunities afforded by this technology. However, it is increasingly observable that social media present enormous risks for individuals, communities, firms, and even for society as a whole. Examples for this “dark side” of social media include cyberbullying, addictive use, trolling, online witch hunts, fake news, and privacy abuse. In this article, we aim to illustrate the multidimensionality of the dark side of social media and describe the related various undesirable outcomes. To do this, we adapt the established social media honeycomb framework to explain the dark side implications of each of the seven functional building blocks: conversations, sharing, presence, relationships, reputation, groups, and identity. On the basis of these reflections, we present a number of avenues for future research, so as to facilitate a better understanding and use of social media.
Diverse Social Media Networks in Public Safety PowerPoint for CCHE 590Nicholas Tancredi
PowerPoint on how social media is used in various Public Safety agencies, including the fact of how it can bridge the communication gap that has been occurring lately.
Social Data and Multimedia Analytics for News and Events ApplicationsYiannis Kompatsiaris
The keynote discusses a framework enabling real-time multimedia indexing and search across multiple social media sources. It places particular emphasis on the real-time, social and contextual nature of content and information consumption in order to integrate topic and event detection, mining, search and retrieval, based on aggregation and indexing of shared user-generated multimedia content. User-friendly applications for the News and Events domains have been developed based on these approaches, incorporating novel user-centric media visualisation and browsing methods. The research and development is part of the FP7 EU project SocialSensor.
Content:
Introduction
Motivation – Challenges
SocialSensor Project and Use Cases
Research Approaches
Large-Scale visual search
Clustering
Verification
Demos – Applications
MM News Demo
Clusttour
Thessfest
Conclusions
These are my slides for a presentation to the CFUW Ontario Council for a workshop aimed at exploring political discourse in an age of misinformation/how to navigate information with a critical eye leading up to the Ontario election. More on the event available here http://cfuwontcouncil.org/standing-committees/
Social Media Mining - Chapter 8 (Influence and Homophily)SocialMediaMining
R. Zafarani, M. A. Abbasi, and H. Liu, Social Media Mining: An Introduction, Cambridge University Press, 2014.
Free book and slides at http://socialmediamining.info/
Chung-Jui LAI - Polarization of Political Opinion by News MediaREVULN
In 2016 US election, social media played a vital role in shaping public opinions as expressed by the news media that have created the phenomenon of polarization in the United States. Because social media gave people the ability to follow, share, post, comment below everything, the phenomenon of political opinions being spread easily and quickly on social media by the news agencies is bringing out a significantly polarized populace.
Consequently, it’s very important to understand the language differences on Twitter and figure out how propaganda spread by different political parties that influence or perhaps mislead public opinion. This talk will introduce the relationship among the social media, public opinion, and news media, then suggests the method to collect the tweets from Twitter and conduct sentimental and logistic regression analysis on them. Furthermore, this talk points out the special aspect on the relationship between the polarization and the topic of this conference (fake news, disinformation and propaganda).
Main points:
- situation in Taiwan
- research on fake news
- methods for fighting fake news
Social Media Mining - Chapter 7 (Information Diffusion)SocialMediaMining
R. Zafarani, M. A. Abbasi, and H. Liu, Social Media Mining: An Introduction, Cambridge University Press, 2014.
Free book and slides at http://socialmediamining.info/
Statement for the Record of Heather Blanchard, Co Founder of CrisisCommons before the Ad Hoc Subcommittee on Disaster Recovery and Intergovernmental Affairs, Homeland Security and Governmental Affairs Committee, United States Senate on May 19, 2011
Human-AI Collaborationfor Virtual Capacity in Emergency Operation Centers (E...Hemant Purohit
Describes different use-cases for how AI technologies can help Emergency Management agencies for building virtual capacity in monitoring online data for situational awareness, decision support, and public communication in EOCs during disaster events.
Talk by Dr. Hemant Purohit, Humanitarian Informatics Lab, George Mason University -- https://mason.gmu.edu/~hpurohit
Social Media, Crisis Communication and Emergency Management: Leveraging Web 2...Connie White
Detailing guidelines and safe practices for using social media across a range of emergency management applications‚ Social Media, Crisis Communication, and Emergency Management: Leveraging Web 2.0 Technologies supplies cutting-edge methods to help you inform the public‚ reduce information overload‚ and ultimately‚ save more lives.
Introduces collaborative mapping tools that can be customized to your needs
Explores free and open-source disaster management systems‚ such as Sahana and Ushahidi
Covers freely available social media technologies—including Facebook‚ Twitter‚ and YouTube
Untapped Potential: Evaluating State Emergency Management Agency Web Sites 2...Dawn Dawson
The 2007-8 Study and Survey that sparked my interest in SMEM and passion for Preparedness & Public Safety . It was clear to me that communicating virtually through various platforms would open communication to the public and could reduce if not eliminate injuries/fatalities. Analysis began in Jan-March, survey in May, myself as Marketing Coordinator C.E.R.T. for the City of Independence/Eastern Jackson County EJC/EOC Fire Station #1 Independence, Mo joined Twitter to show my EM how it could be used on 13 June 2008 . . .
Department of Homeland Security Report- Lessons Learned Using Social Media Du...Mark Rybchuk
What did local governments learn about using social media during a crisis and how did it help serve residents during an emergency? HootSuite Enterprise is referenced on page 33 as one of the key assets the City of New York used during this emergency.
Lessons learned from Social media intervention during hurricane SandyPrayukth K V
Social media and collaborative technologies have become critical components of emergency preparedness, response, and recovery. From the international response efforts in major tsunamis to hurricane response and recovery in major U.S. cities, many government officials now turn to social media technologies to share information and connect with citizens during all phases of a crisis. Implementing these new technologies, however, requires that responding agencies adopt new communication strategies and engagement methods.
Traffic Gridlock: A Bad, Mis-Leading Metaphor that Makes for Bad, Mis-Directe...Barry Wellar
In a previous publication, Traffic Gridlock: The Real Deal or a Pile of Nonsense?, I reported on a study which applied several research procedures to examine media stories and Google search items containing the terms “traffic gridlock” or “gridlock” implying traffic gridlock. The objective was to ascertain whether the media stories and Google items establish that traffic gridlock is a real deal matter, or whether the stories and items contribute to a pile of nonsense. The finding was that 99% of the stories and items belong in the nonsense pile.
And therein lies a puzzle: How is it that “traffic gridlock” enjoys considerable media and Google popularity, but little to no evidence demonstrating the occurrence of “traffic gridlock” accompanies the vast majority of stories and Google entries? In this report I explore one possible explanation, and the associated implication for public policy. That is, traffic gridlock” is a bad, mis-leading metaphor which has been accepted and promulgated by some parties as a truth for which no proof exists and none is needed. And, the associated cause-effect relationship that I comment on is that a bad, mis-leading metaphor is a bad, mis-directed basis for setting public policy.
To support this explanation I introduce the good metaphor “traffic blockage”, and use it as a means to discredit and dismiss the traffic gridlock metaphor which I believe erroneously distorts understanding the role of motor vehicle congestion in urban places, and obscures/confounds the appropriate ways and means of considering and addressing urban motor vehicle congestion. And, as per the initial paper, an invitation is extended to anyone who has traffic gridlock evidence: please call it to my attention at the earliest so that I can adjust my thinking and revise my papers.
Abstract: The wisdom of the crowd is a well-known example of collective intelligence, wherein an aggregated judgment of a group of individuals is superior to that of an individual. The aggregated judgment is surprisingly accurate to predict the outcome of a range of events from geopolitical forecasting to stock price index. Recent research studies have shown that participants’ previous performance data contributes to the identification of a subset of participants that can collectively predict an accurate outcome. In the absence of such performance data, researchers have explored the role of human-perceived diversity to assemble an intelligent crowd. Online social networks are becoming increasingly popular in sharing and seeking domain-specific knowledge. Tapping the crowd wisdom on online social networks can help prediction for several real-world tasks. Independent and contextually diverse crowd selection using social media data imposes unique challenges such as,
Complementing short and potentially noisy social media data with domain specific knowledge.
Lack of labeled data in evaluating closely connected social media participants.
Combining social media text, indicating a diverse perspective, and network features, indicating potential influence, in diverse crowd selection.
Interpretable diversity measure to understand the type of diversity that can enhance the performance of a crowd.
This dissertation first provides several data-driven measures from social-media data and shows that participant diversity can be inferred from social media data and that it can benefit performance in the real world prediction tasks. Domain-specific knowledge graphs provide the foundational basis to evaluate and drive contextually diverse crowd selection and complementing short social media text. Novel group detection and crowd selection algorithms incorporating text, network, and knowledge-graph can automatically select a diverse crowd and also provide recognizable diversity interpretation. It is shown that such a diverse crowd can accurately predict the outcome of real-world events. These results have implications for numerous domains that utilize aggregated judgments - from consumer reviews to econometrics, to geopolitical forecasting and intelligence analysis.
Video: https://youtu.be/KCtoP5u5IqY
Album: https://www.facebook.com/pg/Kno.e.sis/photos/?tab=album&album_id=2538081172893382
Main topics: social media mining, social networks, and influence propagation. Includes an application to social media in disasters.
Talk given at the European Summer School on Information Retrieval (ESSIR 2015) on September 1st, 2015.
See also: http://chato.cl/
Social media? It's serious! Understanding the dark side of social mediaIan McCarthy
Research and practice have mostly focused on the “bright side” of social media, aiming to understand and help in leveraging the manifold opportunities afforded by this technology. However, it is increasingly observable that social media present enormous risks for individuals, communities, firms, and even for society as a whole. Examples for this “dark side” of social media include cyberbullying, addictive use, trolling, online witch hunts, fake news, and privacy abuse. In this article, we aim to illustrate the multidimensionality of the dark side of social media and describe the related various undesirable outcomes. To do this, we adapt the established social media honeycomb framework to explain the dark side implications of each of the seven functional building blocks: conversations, sharing, presence, relationships, reputation, groups, and identity. On the basis of these reflections, we present a number of avenues for future research, so as to facilitate a better understanding and use of social media.
Diverse Social Media Networks in Public Safety PowerPoint for CCHE 590Nicholas Tancredi
PowerPoint on how social media is used in various Public Safety agencies, including the fact of how it can bridge the communication gap that has been occurring lately.
Social Data and Multimedia Analytics for News and Events ApplicationsYiannis Kompatsiaris
The keynote discusses a framework enabling real-time multimedia indexing and search across multiple social media sources. It places particular emphasis on the real-time, social and contextual nature of content and information consumption in order to integrate topic and event detection, mining, search and retrieval, based on aggregation and indexing of shared user-generated multimedia content. User-friendly applications for the News and Events domains have been developed based on these approaches, incorporating novel user-centric media visualisation and browsing methods. The research and development is part of the FP7 EU project SocialSensor.
Content:
Introduction
Motivation – Challenges
SocialSensor Project and Use Cases
Research Approaches
Large-Scale visual search
Clustering
Verification
Demos – Applications
MM News Demo
Clusttour
Thessfest
Conclusions
These are my slides for a presentation to the CFUW Ontario Council for a workshop aimed at exploring political discourse in an age of misinformation/how to navigate information with a critical eye leading up to the Ontario election. More on the event available here http://cfuwontcouncil.org/standing-committees/
Social Media Mining - Chapter 8 (Influence and Homophily)SocialMediaMining
R. Zafarani, M. A. Abbasi, and H. Liu, Social Media Mining: An Introduction, Cambridge University Press, 2014.
Free book and slides at http://socialmediamining.info/
Chung-Jui LAI - Polarization of Political Opinion by News MediaREVULN
In 2016 US election, social media played a vital role in shaping public opinions as expressed by the news media that have created the phenomenon of polarization in the United States. Because social media gave people the ability to follow, share, post, comment below everything, the phenomenon of political opinions being spread easily and quickly on social media by the news agencies is bringing out a significantly polarized populace.
Consequently, it’s very important to understand the language differences on Twitter and figure out how propaganda spread by different political parties that influence or perhaps mislead public opinion. This talk will introduce the relationship among the social media, public opinion, and news media, then suggests the method to collect the tweets from Twitter and conduct sentimental and logistic regression analysis on them. Furthermore, this talk points out the special aspect on the relationship between the polarization and the topic of this conference (fake news, disinformation and propaganda).
Main points:
- situation in Taiwan
- research on fake news
- methods for fighting fake news
Social Media Mining - Chapter 7 (Information Diffusion)SocialMediaMining
R. Zafarani, M. A. Abbasi, and H. Liu, Social Media Mining: An Introduction, Cambridge University Press, 2014.
Free book and slides at http://socialmediamining.info/
Statement for the Record of Heather Blanchard, Co Founder of CrisisCommons before the Ad Hoc Subcommittee on Disaster Recovery and Intergovernmental Affairs, Homeland Security and Governmental Affairs Committee, United States Senate on May 19, 2011
Human-AI Collaborationfor Virtual Capacity in Emergency Operation Centers (E...Hemant Purohit
Describes different use-cases for how AI technologies can help Emergency Management agencies for building virtual capacity in monitoring online data for situational awareness, decision support, and public communication in EOCs during disaster events.
Talk by Dr. Hemant Purohit, Humanitarian Informatics Lab, George Mason University -- https://mason.gmu.edu/~hpurohit
How to Deliver Data Insights by Fmr Google Sr Analytical LeadProduct School
Main takeaways:
- Aligning on an insights definition
- Establish customer / business context before jumping into the data
- Frame your investigation question
- Spend time sanity checking your data / apply street smarts logic
- Use customer / business context to guide exploratory analysis and record observations along the way
- Build a story outline with 1 - 5 supporting insights
- Transcribe the story outline to slide form
During the National Regional Transportation Conference (June 2019, Columbus, OH), Naomi Stein discussed EDR Group's work with the Appalachian Regional Commission to develop a protocol for measuring rural accessibility.
The second of the BDVe series of webinars related to Big Data technologies presents the QROWD project. Elena Simperl (University of Southampton) will provide an overview and technical details on how human interaction and crowdsourcing could help in different steps of the data value chain, from data acquisition to data curation and completion, etc. Examples of how to add human in the loop in the domains of Smart Cities and Smart Transportation will be provided.
The second of the BDVe series of webinars related to Big Data technologies presents the QROWD project. Elena Simperl (University of Southampton) will provide an overview and technical details on how human interaction and crowdsourcing could help in different steps of the data value chain, from data acquisition to data curation and completion, etc. Examples of how to add human in the loop in the domains of Smart Cities and Smart Transportation will be provided.
Social Network Analysis based on MOOC's (Massive Open Online Classes)ShankarPrasaadRajama
Collected data by conducting a survey about MOOC among fellow classmates and created edge lists of students and their skills and students and MOOC websites they do courses using Python from the survey data.
Performed visualization of student network in UCINET and found out the densities among clusters in the network.
Performed hypothesis testing to see whether characteristic of a student affects their position(centrality) in the network.
Every month in the Webinar series a member of our team or invited expert, presents either recent research results or a city case study. The presentations are done online allowing people anywhere to participate and ask questions in real-time. The series address issues relevant to researchers and practitioners and is open to everyone using our news website. About 800 subscribers get the announcement directly, you can also sign up for free here.
Digital Banking / Digital Only Banks is the concept which is recent hot topic in Banking and Fintech. And in advancement and spread of internet and mobile technologies, it's the fantastic concept to remove to need to go to bank physically. However the challenges is roll out of Digital Banks and reaching out to right customer base and keep on growing. Without growth, Digital Banks are dead.
I'm attaching a short presentation on this topic depicting how power of analytics can be leveraged along with marketing tools and techniques to run campaign for digital only banks for lead generation and continuously improving on the campaign.
TOWARDS BUILDING PEOPLE-CENTRIC AI FOR BUSINESS - THE LONG HAULBiplav Srivastava
Presentation given at New York University's Mini Conference -- AI in the Workplace: Future Directions in People Analytics, 2020;
Link: https://wp.nyu.edu/aiatwork/
Minne analytics presentation 2018 12 03 final compressedBonnie Holub
Monday was another great conference by MinneAnalytics! #MinneFRAMA was a great success with over 1,100 attendees at Science Museum of Minnesota. Alison Rempel Brown is a great host! A Teradata colleague told me that her post about my presentation "blew up" with hits and she got over 2K views, and 60+ likes. I'm proud to be a part of this great #datascience organization brining #machinelearning and #artificialintelligence #analytics to our #bigdata clients. If you want my slides, here they are.
Detect Policy-affecting Intent in Twitter Conversations for Rape and Sexual A...Hemant Purohit
This multidisciplinary research investigates Twitter posts related to sexual assaults and rape myths by characterizing and detecting the types of malicious intent, which leads to the beliefs on discrediting women and rape myths. We analyze narrative contexts in which such malicious intents are expressed and discuss their implications for gender violence policy design.
Pandey, R., Purohit, H., Stabile, B., & Grant, A. (2018). Distributional Semantics Approach to Detect Intent in Twitter Conversations on Sexual Assaults. IEEE/WIC/ACM Web Intelligence. ArXiv preprint: https://arxiv.org/abs/1810.01012
Uncertain Concept Graph for Social Web Summarization during Emergencies - CPS18Hemant Purohit
Web has empowered emergency services to enhance operations by collecting real-time information about incidents from diverse data sources such as social media and Web. However, the high volume of unstructured data with varying degrees of veracity challenges the timely extraction and integration of relevant information to summarize the current situation. This research proposes a novel idea of building Uncertain Concept Graphs.
It was presented at 3rd Int’l Workshop on Science of Smart City Operations & Platforms Engineering. Cyber-Physical Systems, CPS Week 2018.
Purohit, H., Nannapaneni, S., Dubey, A., Karuna, P., & Biswas, G. (2018). Structured Summarization of Social Web for Smart Emergency Services by Uncertain Concept Graph. 3rd Int’l Workshop on Science of Smart City Operations & Platforms Engineering. Cyber-Physical Systems (CPS Week).
Humanitarian Informatics Approach for Cooperation between Citizens and Organi...Hemant Purohit
Social networks have empowered citizens to voice their experiences, observations and share information, playing an important role for events related to humanitarian issues. Although a vast amount of data shared on social media may contain valuable information for the decision making, such as response planning in the crisis times, such as situating call for help, and resource availability, the conventional organizational information management face information overload challenge to ingest new information source of citizen-generated data. This paper positions a humanitarian informatics framework to address the information overload problem of organizational actors via a cooperative information system design between citizens and organizations, guided by process knowledge. The framework operationalizes computation into the design process by transforming computationally tractable parts of the design problems into data problems, which meet information needs of organizational actors. This approach can be leveraged for humanitarian problems beyond crisis coordination.
Lessons Learned from PhD Process ExperienceHemant Purohit
Talk at the almamater Kno.e.sis, Wright State Univ., on lessons learned during PhD, and how to cope up when you feel down during PhD or about to start your PhD.
IEEE SocialCom 2015: Intent Classification of Social Media TextHemant Purohit
Social media platforms facilitate the emergence of citizen communities that discuss real-world events, and generate/share content with a variety of intent ranging from social good (e.g., volunteering to help) to commercial interest (e.g., criticizing product features). Hence, mining intent from social data can aid in filtering social media to support organizations, such as an emergency management unit for resource planning. However, effective intent mining is inherently challenging due to ambiguity in interpretation, and sparsity of relevant behaviors in social data. In this research, we address the problem of multiclass classification of intent with a use-case of social data generated during crisis events. Our novel method exploits a hybrid feature representation created by combining top-down processing using knowledge-guided patterns with bottom-up processing using a bag-of-tokens model. We employ pattern-set creation from a variety of knowledge sources including psycholinguistics to tackle the ambiguity challenge, social behavior about conversations to enrich context, and contrast patterns to tackle the sparsity challenge.
ICICT-15 keynote: Big Data Innovation for Social Impact, Hemant PurohitHemant Purohit
This talk presents a case for mining human behavior in the big data generated by citizens on social networks, for meeting organizational information needs of social development and NGO/GO organizations.
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...Subhajit Sahu
Abstract — Levelwise PageRank is an alternative method of PageRank computation which decomposes the input graph into a directed acyclic block-graph of strongly connected components, and processes them in topological order, one level at a time. This enables calculation for ranks in a distributed fashion without per-iteration communication, unlike the standard method where all vertices are processed in each iteration. It however comes with a precondition of the absence of dead ends in the input graph. Here, the native non-distributed performance of Levelwise PageRank was compared against Monolithic PageRank on a CPU as well as a GPU. To ensure a fair comparison, Monolithic PageRank was also performed on a graph where vertices were split by components. Results indicate that Levelwise PageRank is about as fast as Monolithic PageRank on the CPU, but quite a bit slower on the GPU. Slowdown on the GPU is likely caused by a large submission of small workloads, and expected to be non-issue when the computation is performed on massive graphs.
Adjusting primitives for graph : SHORT REPORT / NOTESSubhajit Sahu
Graph algorithms, like PageRank Compressed Sparse Row (CSR) is an adjacency-list based graph representation that is
Multiply with different modes (map)
1. Performance of sequential execution based vs OpenMP based vector multiply.
2. Comparing various launch configs for CUDA based vector multiply.
Sum with different storage types (reduce)
1. Performance of vector element sum using float vs bfloat16 as the storage type.
Sum with different modes (reduce)
1. Performance of sequential execution based vs OpenMP based vector element sum.
2. Performance of memcpy vs in-place based CUDA based vector element sum.
3. Comparing various launch configs for CUDA based vector element sum (memcpy).
4. Comparing various launch configs for CUDA based vector element sum (in-place).
Sum with in-place strategies of CUDA mode (reduce)
1. Comparing various launch configs for CUDA based vector element sum (in-place).
Automatically Rank Social Media Requests for Emergency Services using Serviceability Model - ASONAM18
1. Social-EOC: Serviceability Model To Rank Social Media
Requests for Emergency Operation Centers
Hemant Purohit, Rahul Pandey
Humanitarian, Semantics &
Informatics Lab (Human_Info_Lab)
The 2018 IEEE/ACM International Conference on
Advances in Social Networks Analysis and Mining (ASONAM-2018)
Barcelona, Spain
Aug 29, 2018
Carlos Castillo
Web Science & Social
Computing Research Group
Muhammad Imran
Crisis Computing & Social
Computing Group
@hemant_pt @chaToX @mimran15 @gizmowiki
2. Serviceability Model for Social Media Services, ASONAM-18
Outline
¨ Introduction
n Social media & web streams during disasters
n Problem: filter and rank requests for help
¨ Background and Related Work
n Services in emergency management
n Social computing for emergency management
n Mining request / help-seeking intent
¨ Social-EOC: Serviceability Model
n Qualitative and quantitative formulation
n Social-EOC based Learning-to-Rank system
¨ Experiments
n Conversational data collection
n Learning-to-Rank evaluation
¨ Results
¨ Discussion and Future Work
2
3. Serviceability Model for Social Media Services, ASONAM-18
Social Media & Web Use in Disasters
3
When traditional call systems are exhausted ..
Source: https://www.usatoday.com/story/news/nation-now/2017/08/27/desperate-help-flood-victims-houston-turn-twitter-rescue/606035001/
4. Serviceability Model for Social Media Services, ASONAM-18
Mining Social & Web Data: Innovation
Opportunity for Emergency Services
4
But ..
WHAT & HOW
to filter?
5. Serviceability Model for Social Media Services, ASONAM-18
Mining Social & Web Data: Relevancy issue
5
6. Serviceability Model for Social Media Services, ASONAM-18
Mining Social & Web Data: Ranking issue
(Anonymized) Message Serviceable Degree
@_USER_ I am 9 ft above current water levels,
why am I told to evacuate Grand Lakes now?
Please advise.
serviceable
@_USER_ If there has been no rain since
yesterday, why is water not draining?
Serviceable but lacks details
@_USER_ Thank God you are working on this.
Let us chat when things settle down
not serviceable
¨ Illustration from Hurricane Harvey 2017
6
7. Serviceability Model for Social Media Services, ASONAM-18
Problem
7
¨ Can we filter/classify and prioritize/rank serviceable
social media requests for emergency services?
¨ Scope:
¤ Study requests directly sent to the accounts of services
¤ Analyze the requests during a disaster event
8. Serviceability Model for Social Media Services, ASONAM-18
Mining Social & Web Data: Challenges
¨ Variable Actionability
¤ Subjective relevance of messages, often task-
dependent
¨ Insufficient Samples
¤ Limited context representativeness of request samples
to directly learn ranking
8
9. Serviceability Model for Social Media Services, ASONAM-18
Solution: Our Contributions
9
¨ Novel generalizable model (Social-EOC) to define serviceability
characteristics of a service request message on social media
¨ Learning-to-rank system based on the Social-EOC model
¤ Inference of the serviceability characteristics
¤ Classification and ranking of serviceable requests
¨ Evaluation of the Social-EOC model with the datasets from six
crisis events
10. Serviceability Model for Social Media Services, ASONAM-18
Outline
¨ Introduction
n Social media & web streams during disasters
n Problem: filter and rank requests for help
¨ Background and Related Work
n Services in emergency management
n Social computing for emergency management
n Mining request/ help-seeking intent
¨ Social-EOC: Serviceability Model
n Qualitative and quantitative formulation
n Social-EOC based Learning-to-Rank system
¨ Experiments
n Conversational data collection
n Learning-to-Rank evaluation
¨ Results
¨ Discussion and Future Work
10
11. Serviceability Model for Social Media Services, ASONAM-18
Services in Emergency Management (EM)
¨ Incident-Command System (ICS) model for the response coordination
11
Public Info. Officer (PIO)
provides the information
services [FEMA; Hughes & Palen,
JHSEM 2012]
FEMA: https://training.fema.gov/ programs/pio/ Source: https://en.wikipedia.org/wiki/Incident_Command_System
12. Serviceability Model for Social Media Services, ASONAM-18
Social Computing for EM: Crisis Informatics
12
¨ Extensive literature on social media during disasters [Castillo,
Cambridge Press 2016; Imran et al., CSUR 2015]
¤ Addressed a variety of problems [c.f. Tutorial: Castillo, Diaz & Purohit, SDM 2014]
n Data collection and filtering[e.g., Olteanu et al., ICWSM 2014]
n Modeling actionable help behavior [e.g., Purohit et al., SocialCom 2015]
n Summarization [e.g., Rudra et al., HyperText 2016]
n Information diffusion [e.g., Starbird & Palen, ISCRAM 2010]
n Information and source credibility [e.g., Castillo et al., WWW 2011]
n Visual analytics [e.g., Kumar et al., ICWSM 2011]
n ..
¨ Open problem: finding formal characteristics of relevant
social media requests that must be prioritized
13. Serviceability Model for Social Media Services, ASONAM-18
Mining Request/Seeking Intent
13
REQUEST MEDIUM TYPE FOCUS
Emails
Finding and ranking messages to reply with
different interpersonal communication
behavior for information seeking
[Yang et al., SIGIR 2017; Lampert et al., HLT 2010]
Q&A Forums
Generic seeking behavior for all types of
users and often not targeted towards
answers from a specific organization/group
[Mai, Emerald 2016; Vasilescu et al., CSCW 2014]
Social Media Chats
Finding explicit or implicit requests for help
during disaster relief and users who could
answer queries [Purohit et al., First Monday 2013;
He et al., WebSci 2017; Ranganath et al., TKDE 2017;
Sachdeva & Kumaraguru, CSCW 2017]
14. Serviceability Model for Social Media Services, ASONAM-18
Outline
¨ Introduction
n Social media & web streams during disasters
n Problem: filter and rank requests for help
¨ Background and Related Work
n Services in emergency management
n Social computing for emergency management
n Mining requests / help-seeking intent
¨ Social-EOC: Serviceability Model
n Qualitative and quantitative formulation
n Social-EOC based Learning-to-Rank system
¨ Experiments
n Conversational data collection
n Learning-to-Rank evaluation
¨ Results
¨ Discussion and Future Work
14
15. Serviceability Model for Social Media Services, ASONAM-18
Social-EOC Serviceability Model:
Qualitative Domain Knowledge based on FEMA PIO Guide
15
Explicit
Request
E(m)
Answerable
Query
A(m)
Sufficiently
Detailed
D(m)
Correctly
Addressed
C(m)
Serviceability(m) = f ( E(m), A(m), D(m), C(m) )
Explicitly asks for a
resource or service
Explicitly asks a question
that can be answered
Sent to organization or
person who could have
resources or provide the
service, an alarm, or
could answer questions
Specifying contextual
information: time (when),
location (where),
quantity (how much),
resource (which)
16. Serviceability Model for Social Media Services, ASONAM-18
Serviceability Model: Quantifying Characteristics
(Anonymized) Message Explicit Answer-
able
Addressed Detailed
@account1 please, governor, post a phone # for
specific info in our local areas
4.3 4.3 3.3 3.7
@account2 is thr parking at McMahon for volunteer? 4.0 5.0 5.0 5.0
@account3 how can I help 1.3 4.3 4.3 1.0
@account4 Plz pray for these families 1.7 1.0 1.0 1.0
@account5 been working in #LAFlood shelter, we
actively monitor SM for feedback
1.0 1.0 2.0 2.0
“@account7 No matter where in the world ur
followers live, you can donate from link Plz RT
1.0 1.0 1.0 1.0
¨ E(m), A(m), C(m), D(m) : Likert Scale Functions [score:1-5]
16
Illustration Table: Average scores of Likert ratings by crowd annotators
17. Serviceability Model for Social Media Services, ASONAM-18
Learning-to-Rank System Design: Using Social-
EOC Model
17
18. Serviceability Model for Social Media Services, ASONAM-18
Learning-to-Rank System Design: Steps
18
1. Collecting conversation chains of seed messages
n A seed message mentions a targeted account of official services (e.g.,
@fboem for ‘Fort Bend County OEM’) identified using gov./news reports
2. Rating serviceability characteristics of a request
n Also additional category ‘Other’: advertisements, jokes, ..
n Annotation by crowdsourcing workers
3. Creating gold standard of serviceable requests
n Binary classes: Serviceable (relevant), Not-Serviceable (Not relevant)
n Annotation by Emergency Management professionals
4. Learning to classify and rank serviceable requests
n SVM-Rank
n Relevance grade levels: binary
19. Serviceability Model for Social Media Services, ASONAM-18
Outline
¨ Introduction
n Social media & web streams during disasters
n Problem: filter and rank requests for help
¨ Related Work
n Services in emergency management
n Social computing for emergency management
n Mining requests / help-seeking intent
¨ Social-EOC: Serviceability Model
n Qualitative and quantitative formulation
n Social-EOC based Learning-to-Rank system
¨ Experiments and Results
n Conversational data collection
n Learning-to-Rank evaluation
n Results
¨ Discussion and Future Work
19
20. Serviceability Model for Social Media Services, ASONAM-18
Experiments
20
¨ Data
¤ Collected Twitter messages related to 6 crisis events:
n Big: Hurricane Harvey 2017, Nepal Earthquake 2015, Alberta Floods 2013
n Small: Louisiana Floods 2016, Oklahoma Tornado 2013, Hurricane Sandy 2012
¤ Crawl Twitter conversation chains for seed messages
21. Serviceability Model for Social Media Services, ASONAM-18
Experiments
21
¨ Feature (f.) extraction for Learning-to-Rank method
¤ Generic f.: number of words, hashtags, mentions, and URLs in a tweet
¤ Text f.: tf-idf with Bag-of-Words representation
¤ Manual serviceable f.: average annotation rating between 1 to 5
for each serviceable characteristic
¤ Inferred serviceable f.: 0 or 1
n Binary classifier for each characteristic (rating 1-2: negative, 3-5: positive
class}
¨ Evaluation metric for top-K ranked results
¤ Normalized Discounted Cumulative Gain (NDCG)
¤ NDCG @10
22. Serviceability Model for Social Media Services, ASONAM-18
Experiments: Evaluation Schemes
22
LTR models based on varied features (f.):
¨ [T]: Text f. and generic f. (baseline)
¨ [T+I]: T and inferred serviceable f. from the model built on the
same event data
¤ [T + I_all]: T and inferred serviceable f. from the model built
on the all events data
¤ [T + I_cross]: T and inferred serviceable f. from the model
built on the cross events data (all except the current)
¤ [T_cross + I_cross]: both T and inferred serviceable f. from the
model built on the cross events data (all except the current)
¨ [T+M]: T + manual serviceable f.
23. Serviceability Model for Social Media Services, ASONAM-18
Results
1. Models with inferred
serviceable features
are generally better
than the baseline.
2. Performance varies in
cases of small datasets.
n less training examples
n imbalanced
23
24. Serviceability Model for Social Media Services, ASONAM-18
Results
3. Cross-event models
perform well.
n especially for smaller
datasets
4. Serviceability
characteristics based
features are among the
best discriminators.
n among the top-5 features,
identified using χ2 test
24
25. Serviceability Model for Social Media Services, ASONAM-18
Discussion: Examples of Resulting Ranked Requests
25
Ranked Messages by T (text)+I (Inferred) Modeling Scheme
TOP-2
[Sandy]
- @_USER_ please, governor, post a website or phone# where we can get
specific info for our local areas
- @_USER_ Queens trains aren’t being addressed at all. When can v expect any
service updates for the NQR trains?
BOTTOM-2
[Sandy]
- @_USER_ Romney not going2like that gov christie is being nice about Obama’s
leadership
- @_USER_ HILARIOUS! That’s much needed laughter, I am sure.
TOP-2
[Alberta]
- @_USER_ can you tell me if sanitary pumps are running yet in elbow park?
#yycflood
- @_USER_ plz text with what you need & address. Lots of volunteers in mission
BOTTOM-2
[Alberta]
- @_USER_ thank u calgary police
- @_USER_ Tx for ur time!!
26. Serviceability Model for Social Media Services, ASONAM-18
Discussion: Future Application for Prioritization of
Streaming Messages
26
Serviceability
Source: https://blog.bufferapp.com/twitter-timeline-algorithm
BEYOND TIME & CREDIBILITY,
RANK BY
27. Serviceability Model for Social Media Services, ASONAM-18
Discussion: Lessons, Limitations and Future Work
27
¨ Lessons learned:
n Serviceability characteristics capture the notion of relevance and
serviceability for social media requests to organizational services.
n Experimented for binary relevance (serviceability) grades, but the method is
extensible for multiple grade levels.
¨ Limitations & opportunities for future work
n Study non-English language request messages
n Explore multiple as opposed to single platform based datasets
n Include indirectly addressed request messages (i.e. not starting with @user)
n Generate optimal request alerts to respond
n Our new work: Purohit, Castillo, Imran, Pandey (2018, to appear). Ranking of Social
Media Alerts with Workload Bounds in Emergency Operation Centers. Web Intelligence.
28. Serviceability Model for Social Media Services, ASONAM-18
Conclusion
¨ Demonstrated that social media requests have some common
core characteristics for helping rank the serviceable requests
for organizational services.
¨ Presented a novel qualitative-quantitative model for
serviceable request characteristics for emergencies and
demonstrated its use by Learning-to-Rank (LTR) methodology.
¨ Evaluated LTR systems based on inclusion of serviceability
characteristics features across six disaster events and noted a
superior performance (gain up to 25% in nDCG@10 and nDCG@5).
28
29. Serviceability Model for Social Media Services, ASONAM-18
PAPER: http://ist.gmu.edu/~hpurohit/informatics-
lab/papers/serviceability_ranking_disasters_ASONAM18_final.pdf
CONTACT: hpurohit@gmu.edu
Acknowledgement:
image sources, collaborators (especially Profs. Amit Sheth, Valerie Shalin, & TK Prasad at Kno.e.sis Center;
U.S. DHS Science & Technology SMWGESDM Researcher-Practitioner Subgroup), Human_Info_lab Alumni
(Yogen, Sharan) as well as sponsors:
Questions?
29
Grants:
IIS #1657379,
IIS #1815459
La Caixa project:
LCF/PR/PR16/11110009