Show simple item record

dc.contributor.advisorRoy E. Welsch and Peter Szolovits.en_US
dc.contributor.authorPlmanabhan, Jaya Prasaden_US
dc.contributor.otherMassachusetts Institute of Technology. Engineering Systems Division.en_US
dc.date.accessioned2017-01-06T16:14:42Z
dc.date.available2017-01-06T16:14:42Z
dc.date.copyright2015en_US
dc.date.issued2015en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/106270
dc.descriptionThesis: S.M. in Engineering and Management, Massachusetts Institute of Technology, School of Engineering, System Design and Management Program, Engineering and Management Program, 2015.en_US
dc.descriptionThesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2015.en_US
dc.descriptionCataloged from PDF version of thesis.en_US
dc.descriptionIncludes bibliographical references (pages 150-154).en_US
dc.description.abstractIt is common practice in organizational research to apply policy analysis to better understand how an enterprise is approaching and addressing a particular topic of interest. The approach to policy analysis commonly used is known as the Coding Approach. The Coding Approach is a highly qualitative process that involves the manual identification of relevant policy documents, the manual review of these documents to identify the key features of the topic, and the manual identification of the significance of these features as it relates to the policy documents. This process can generates rich insights into policies and how the topic of interest is being approached and viewed by the Stakeholder of the enterprise. This process however is a manually intensive process and is subject to the bias of the expert/s reviewing and analyzing the documents. My study proposes a new approach towards policy analysis that uses the Coding Approach as its template, but applies Machine Learning Techniques, such as Natural Language Processing and Data Mining Algorithms, together with a highly structured form of Case and Cross Case Analysis to identify documents that are related to the topic of interest, to categorize these documents, to surface the key features of the topic, to calculate the significance of these features as reflected by the documents and to draw inferences about the key features and its significance as it relates to the policy documents. This new approach provides a mixed methods approach that marries the best of both quantitative and qualitative techniques towards document analysis. This approach also reduces the amount bias that can be injected from the experts analyzing the documents, and thus guarantees an almost consistent result from document analysis regardless of the experts performing the analysis. For my study I applied my mixed methods approach to analyzing the policy documents of the Military Health Enterprise MHS, to understand how well the MHS 's policies were addressing the delivery of psychological services to service members and their families. This study is important to the MHS for two reasons. With the reductions of the US Military presence in Afghanistan and Iraq there are large numbers of veterans returning who may have various forms of PTSD, who will requires varying types and levels of care. The other reason why this study is important to the MHS is due to the recent scandals (Walter Reed, 2007 & VA, 2014) it has faced specifically around to the health care services it was supposed to provide to service members. Now its crucial for the MHS to understand the disconnect between its policies and what's actually being implemented. This study will provide the MHS with a non-bias review of what are the features of significance from a policy point of view in regards to the delivery of psychological services to service members and their families.en_US
dc.description.statementofresponsibilityby Jaya Prasad Plmanabhan.en_US
dc.format.extent154 pagesen_US
dc.language.isoengen_US
dc.publisherMassachusetts Institute of Technologyen_US
dc.rightsM.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.en_US
dc.rights.urihttp://dspace.mit.edu/handle/1721.1/7582en_US
dc.subjectEngineering and Management Program.en_US
dc.subjectSystem Design and Management Program.en_US
dc.subjectElectrical Engineering and Computer Science.en_US
dc.subjectEngineering Systems Division.en_US
dc.titleApplying machine learning techniques to the analysis of policy data of the military health enterpriseen_US
dc.typeThesisen_US
dc.description.degreeS.M. in Engineering and Managementen_US
dc.description.degreeS.M.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Engineering and Management Programen_US
dc.contributor.departmentSystem Design and Management Program.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
dc.identifier.oclc963232581en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record