Crowdsourcing as a Map Reduce Job
Navy SBIR FY2013.1

Sol No.: Navy SBIR FY2013.1
Topic No.: N131-063
Topic Title: Crowdsourcing as a Map Reduce Job
Proposal No.: N131-063-0012
Firm: Management Sciences, Inc.
6022 Constitution Avenue NE
Albuquerque, New Mexico 87110-5941
Contact: Kshanti Greene
Phone: (505) 255-8611
Web Site:
Abstract: MSI proposes to develop automated mechanisms to dissect incoming queries and engage appropriate cloud-based resources to address them. To automate this process, we propose iterative query refinement between an automated analyzer (called the Matchmaker) and human experts. The Matchmaker will use keyword and semantic analysis to identify query topics. These topics will engage people with expertise in those topics who can either take on the subtasks or provide more accurate topic suggestions. When the task results are submitted, an automated Fusion Engine will compare all results with a description of the expected results (submitted by the task creator) and select the best answer. These mechanisms will extend MSI's foundational system for massively collaborative problem solving that is being developed for a Phase II DARPA SBIR. Our framework, called ePluribus, allows collaborators to explore two key problem solving phases: understanding the situation that brought about the problem and evaluating actions that can modify the outcome of the situation. Similar to the map/reduce model, ePluribus allows people to 1) decompose complex problems into manageable components (map), 2) asynchronously provide solutions to these sub-problems, and then 3) aggregate the proposed solutions to form a collective solution integrating all significant points of view (reduce).
Benefits: The commercial potential of ePluribus comes from the power of ePluribus tools to redirect dynamic human feedback from social networking sites, online gaming environments, cell-phones, focus groups, blogs and online opinion polls to form solutions to complex multi-scale problems. We see the ePluribus changing the way communities, agencies, political and non-profit organizations address pressing issues affecting world societies such as recessions, health care, military conflicts, natural disasters, climate change and energy sustainability. The complete line of ePluribus tools will leverage human insight for social problem solving, decision-making and prediction to develop holistic solutions to problems that plague society, taking into consideration the concerns of stakeholders and the ideas of experts, citizens and public servants. This Phase I effort, if successful, will add important functionality to our existing ePluribus framework for collective problem-solving. The automated mechanisms to decompose problems and fuse solutions will reduce the load on human contributors. In particular, decomposition will provide relevant topics for people to start from, instead of requiring them to manually break down the problem into tasks that they can take on. Automated methods to manage the reduce phase- or selecting best answers, will provide a more objective way to aggregate human feedback. Finally, the extensions will allow us to apply ePluribus to crisis response- an area that has a significant need for ad hoc situation analysis and coordination in emergent events.