Show simple item record

dc.contributor.advisorHenry A. Lieberman.en_US
dc.contributor.authorChen, Ge (Ge Jackie)en_US
dc.contributor.otherMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.en_US
dc.date.accessioned2014-11-04T20:28:55Z
dc.date.available2014-11-04T20:28:55Z
dc.date.copyright2014en_US
dc.date.issued2014en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/91306
dc.descriptionThesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2014.en_US
dc.descriptionThis electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.en_US
dc.description21en_US
dc.descriptionCataloged from student-submitted PDF version of thesis.en_US
dc.descriptionIncludes bibliographical references (pages 53-54).en_US
dc.description.abstractCrisis Text Line supports people with mental health issues through texting. Unfortunately, support is limited by the number of counselors and the time each counselor has for clients, as well as the cognitive load on counselors from managing multiple conversations simultaneously. We conducted a contextual inquiry with crisis counselors to find contributing problems in their work flow. We believe topic modeling can provide automatic summaries of conversation text to augment note-taking and transcript-reading. Four simple and familiar visualizations were developed to present the model data: 1) a list of conversation topics, 2) a donut chart of topic percentages, 3) a line chart of topic trends, and 4) a scatter plot of specific topic points in the text. Our hypothesis is that these visualizations will help counselors spend more time on clients without overloading the counselors. The visualizations were evaluated through a user study to determine their effectiveness against a control interface.en_US
dc.description.statementofresponsibilityby Ge (Jackie) Chen.en_US
dc.format.extent54 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.subjectElectrical Engineering and Computer Science.en_US
dc.titleVisualizations for mental health topic modelsen_US
dc.typeThesisen_US
dc.description.degreeM. Eng.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
dc.identifier.oclc893856032en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record