�ݺ�ߣshows by User: hemant

�ݺ�ߣshows by User: hemant_pt / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: hemant_pt / Mon, 29 Apr 2024 20:04:14 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: hemant_pt Human-AI Collaboration�for Virtual Capacity in Emergency Operation Centers (EOCs) /slideshow/humanai-collaborationfor-virtual-capacity-in-emergency-operation-centers-eocs/267646977 pnnl-emotr-talk-apr29-240429200414-d40923d9
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 ]]>
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 ]]> Mon, 29 Apr 2024 20:04:14 GMT /slideshow/humanai-collaborationfor-virtual-capacity-in-emergency-operation-centers-eocs/267646977 hemant_pt@slideshare.net(hemant_pt) Human-AI Collaboration�for Virtual Capacity in Emergency Operation Centers (EOCs) hemant_pt 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 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/pnnl-emotr-talk-apr29-240429200414-d40923d9-thumbnail.jpg?width=120&height=120&fit=bounds" /> 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

Human-AI Collaboration for Virtual Capacity in Emergency Operation Centers (EOCs) from Hemant Purohit

]]> 171 0 https://cdn.slidesharecdn.com/ss_thumbnails/pnnl-emotr-talk-apr29-240429200414-d40923d9-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Detect Policy-affecting Intent in Twitter Conversations for Rape and Sexual Assaults - Web-Intelligence 2018 /slideshow/distributional-semantics-approach-to-detect-policyaffecting-intent-in-twitter-conversations-for-rape-and-sexual-assaults/125090018 ieee-web-intelligence-policy-affecting-intent-mining-181205202130
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]]>
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]]> Wed, 05 Dec 2018 20:21:29 GMT /slideshow/distributional-semantics-approach-to-detect-policyaffecting-intent-in-twitter-conversations-for-rape-and-sexual-assaults/125090018 hemant_pt@slideshare.net(hemant_pt) Detect Policy-affecting Intent in Twitter Conversations for Rape and Sexual Assaults - Web-Intelligence 2018 hemant_pt 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 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/ieee-web-intelligence-policy-affecting-intent-mining-181205202130-thumbnail.jpg?width=120&height=120&fit=bounds" /> 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

Detect Policy-affecting Intent in Twitter Conversations for Rape and Sexual Assaults - Web-Intelligence 2018 from Hemant Purohit

]]> 451 1 https://cdn.slidesharecdn.com/ss_thumbnails/ieee-web-intelligence-policy-affecting-intent-mining-181205202130-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Workload-bound Ranking of Alerts for Emergency Operation Centers - Web Intelligence 2018 /hemant_pt/workloadbound-ranking-of-alerts-for-emergency-operation-centers-web-intelligence-2018 ieee-webintelligence18-workload-bound-ranking-alerts-181205155927
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]]>
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]]> Wed, 05 Dec 2018 15:59:27 GMT /hemant_pt/workloadbound-ranking-of-alerts-for-emergency-operation-centers-web-intelligence-2018 hemant_pt@slideshare.net(hemant_pt) Workload-bound Ranking of Alerts for Emergency Operation Centers - Web Intelligence 2018 hemant_pt 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 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/ieee-webintelligence18-workload-bound-ranking-alerts-181205155927-thumbnail.jpg?width=120&height=120&fit=bounds" /> 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

Workload-bound Ranking of Alerts for Emergency Operation Centers - Web Intelligence 2018 from Hemant Purohit

]]> 404 5 https://cdn.slidesharecdn.com/ss_thumbnails/ieee-webintelligence18-workload-bound-ranking-alerts-181205155927-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Automatically Rank Social Media Requests for Emergency Services using Serviceability Model - ASONAM18 /slideshow/serviceability-model-to-rank-social-media-requests-for-emergency-services-asonam18/112217273 asonam18-serviceability-rankingemergencyservices-180830053240
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. ]]>
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. ]]> Thu, 30 Aug 2018 05:32:40 GMT /slideshow/serviceability-model-to-rank-social-media-requests-for-emergency-services-asonam18/112217273 hemant_pt@slideshare.net(hemant_pt) Automatically Rank Social Media Requests for Emergency Services using Serviceability Model - ASONAM18 hemant_pt 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. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/asonam18-serviceability-rankingemergencyservices-180830053240-thumbnail.jpg?width=120&height=120&fit=bounds" /> 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.

Automatically Rank Social Media Requests for Emergency Services using Serviceability Model - ASONAM18 from Hemant Purohit

]]> 9755 6 https://cdn.slidesharecdn.com/ss_thumbnails/asonam18-serviceability-rankingemergencyservices-180830053240-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Social Media & Web Mining for Public Services of Smart Cities - SSA Talk /slideshow/social-media-web-mining-for-public-services-of-smart-cities-ssa-talk/109730161 ssa-talk-aug13-hemantpurohit-final-180813201848
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. ]]>
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. ]]> Mon, 13 Aug 2018 20:18:48 GMT /slideshow/social-media-web-mining-for-public-services-of-smart-cities-ssa-talk/109730161 hemant_pt@slideshare.net(hemant_pt) Social Media & Web Mining for Public Services of Smart Cities - SSA Talk hemant_pt 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. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/ssa-talk-aug13-hemantpurohit-final-180813201848-thumbnail.jpg?width=120&height=120&fit=bounds" /> 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.

Social Media & Web Mining for Public Services of Smart Cities - SSA Talk from Hemant Purohit

]]> 9622 5 https://cdn.slidesharecdn.com/ss_thumbnails/ssa-talk-aug13-hemantpurohit-final-180813201848-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Uncertain Concept Graph for Social Web Summarization during Emergencies - CPS18 /slideshow/uncertain-concept-graph-for-social-web-summarization-during-emergencies-cps18-93459090/93459090 scopegctc-cps18-disaster-summarizationv3-180410155659
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). ]]>
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). ]]> Tue, 10 Apr 2018 15:56:59 GMT /slideshow/uncertain-concept-graph-for-social-web-summarization-during-emergencies-cps18-93459090/93459090 hemant_pt@slideshare.net(hemant_pt) Uncertain Concept Graph for Social Web Summarization during Emergencies - CPS18 hemant_pt 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). <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/scopegctc-cps18-disaster-summarizationv3-180410155659-thumbnail.jpg?width=120&height=120&fit=bounds" /> 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).

Uncertain Concept Graph for Social Web Summarization during Emergencies - CPS18 from Hemant Purohit

]]> 328 3 https://cdn.slidesharecdn.com/ss_thumbnails/scopegctc-cps18-disaster-summarizationv3-180410155659-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 User Classification of Organization and Organization Affiliated Users during Crisis Events /hemant_pt/user-classification-of-organization-and-organization-affiliated-users-during-crisis-events iscram17-userorg-may22-170522085009
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. ]]>
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. ]]> Mon, 22 May 2017 08:50:08 GMT /hemant_pt/user-classification-of-organization-and-organization-affiliated-users-during-crisis-events hemant_pt@slideshare.net(hemant_pt) User Classification of Organization and Organization Affiliated Users during Crisis Events hemant_pt 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. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/iscram17-userorg-may22-170522085009-thumbnail.jpg?width=120&height=120&fit=bounds" /> 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.

User Classification of Organization and Organization Affiliated Users during Crisis Events from Hemant Purohit

]]> 334 2 https://cdn.slidesharecdn.com/ss_thumbnails/iscram17-userorg-may22-170522085009-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Public Health Crisis Analytics for Gender Violence /slideshow/public-health-crisis-analytics-for-genderbased-violence/75757676 gmu-healthsympo-gbv-apr20-170507202237
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. ]]>
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. ]]> Sun, 07 May 2017 20:22:37 GMT /slideshow/public-health-crisis-analytics-for-genderbased-violence/75757676 hemant_pt@slideshare.net(hemant_pt) Public Health Crisis Analytics for Gender Violence hemant_pt 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. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/gmu-healthsympo-gbv-apr20-170507202237-thumbnail.jpg?width=120&height=120&fit=bounds" /> 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.

Public Health Crisis Analytics for Gender Violence from Hemant Purohit

]]> 6929 4 https://cdn.slidesharecdn.com/ss_thumbnails/gmu-healthsympo-gbv-apr20-170507202237-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Humanitarian Informatics Approach for Cooperation between Citizens and Organizations - CSCW16 CADMICS talk /hemant_pt/cscw2016cadmicstalkpurohit cscw-cadmics16-talk-purohit-160303000611
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. ]]>
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. ]]> Thu, 03 Mar 2016 00:06:11 GMT /hemant_pt/cscw2016cadmicstalkpurohit hemant_pt@slideshare.net(hemant_pt) Humanitarian Informatics Approach for Cooperation between Citizens and Organizations - CSCW16 CADMICS talk hemant_pt 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. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/cscw-cadmics16-talk-purohit-160303000611-thumbnail.jpg?width=120&height=120&fit=bounds" /> 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.

Humanitarian Informatics Approach for Cooperation between Citizens and Organizations - CSCW16 CADMICS talk from Hemant Purohit

]]> 721 6 https://cdn.slidesharecdn.com/ss_thumbnails/cscw-cadmics16-talk-purohit-160303000611-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Lessons Learned from PhD Process Experience /slideshow/lessons-learned-from-phd-process-experience/56921261 phd-experience-lessons-160111183037
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. ]]>
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. ]]> Mon, 11 Jan 2016 18:30:37 GMT /slideshow/lessons-learned-from-phd-process-experience/56921261 hemant_pt@slideshare.net(hemant_pt) Lessons Learned from PhD Process Experience hemant_pt 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. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/phd-experience-lessons-160111183037-thumbnail.jpg?width=120&height=120&fit=bounds" /> 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.

Lessons Learned from PhD Process Experience from Hemant Purohit

]]> 1173 10 https://cdn.slidesharecdn.com/ss_thumbnails/phd-experience-lessons-160111183037-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 IEEE SocialCom 2015: Intent Classification of Social Media Text /slideshow/ieee-socialcom-2015-intent-classification-of-social-media-text/56448437 ieee-socialcom-2015-v2-151226025018
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.]]>
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.]]> Sat, 26 Dec 2015 02:50:18 GMT /slideshow/ieee-socialcom-2015-intent-classification-of-social-media-text/56448437 hemant_pt@slideshare.net(hemant_pt) IEEE SocialCom 2015: Intent Classification of Social Media Text hemant_pt 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. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/ieee-socialcom-2015-v2-151226025018-thumbnail.jpg?width=120&height=120&fit=bounds" /> 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.

IEEE SocialCom 2015: Intent Classification of Social Media Text from Hemant Purohit

]]> 1230 9 https://cdn.slidesharecdn.com/ss_thumbnails/ieee-socialcom-2015-v2-151226025018-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 ICICT-15 keynote: Big Data Innovation for Social Impact, Hemant Purohit /slideshow/icict15-keynote-big-data-innovation-for-social-impact-hemant-purohit/56436742 icict-15-keynote-hemant-purohit-151225033235
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. ]]>
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. ]]> Fri, 25 Dec 2015 03:32:35 GMT /slideshow/icict15-keynote-big-data-innovation-for-social-impact-hemant-purohit/56436742 hemant_pt@slideshare.net(hemant_pt) ICICT-15 keynote: Big Data Innovation for Social Impact, Hemant Purohit hemant_pt 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. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/icict-15-keynote-hemant-purohit-151225033235-thumbnail.jpg?width=120&height=120&fit=bounds" /> 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.

ICICT-15 keynote: Big Data Innovation for Social Impact, Hemant Purohit from Hemant Purohit

]]> 749 7 https://cdn.slidesharecdn.com/ss_thumbnails/icict-15-keynote-hemant-purohit-151225033235-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 https://cdn.slidesharecdn.com/profile-photo-hemant_pt-48x48.jpg?cb=1714420450 Inter-disciplinary research, Social Computing, Intent Mining, User Modeling, Cooperative Systems, Knowledge Graph, Humanitarian Informatics, Crisis Coordination #Tech4SocialGood ist.gmu.edu/~hpurohit https://cdn.slidesharecdn.com/ss_thumbnails/pnnl-emotr-talk-apr29-240429200414-d40923d9-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/humanai-collaborationfor-virtual-capacity-in-emergency-operation-centers-eocs/267646977 Human-AI Collaboration... https://cdn.slidesharecdn.com/ss_thumbnails/ieee-web-intelligence-policy-affecting-intent-mining-181205202130-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/distributional-semantics-approach-to-detect-policyaffecting-intent-in-twitter-conversations-for-rape-and-sexual-assaults/125090018 Detect Policy-affectin... https://cdn.slidesharecdn.com/ss_thumbnails/ieee-webintelligence18-workload-bound-ranking-alerts-181205155927-thumbnail.jpg?width=320&height=320&fit=bounds hemant_pt/workloadbound-ranking-of-alerts-for-emergency-operation-centers-web-intelligence-2018 Workload-bound Ranking...