The scheduling conflict is due to me, and we have another presenter in the same
room on 9 Sept. If you are interested in attending the 9 Sept presentation,
here are the details. The event is free and being sponsored by the Ft. Huachuca
IEEE chapter.
Bear Down,
John
UA Eller College (Business and MIS) Professor Gondy Leroy will give a talk on
Medical Informatics - the merging of data and medicine. The meeting will be on
9 September from 1700 to 1900 at the UA Sierra Vista Campus room C165A, hosted
by UA South Continuing Education and sponsored by IEEE Fort Huachuca Section.
RSVP to Dr. John DeLalla (jd@xxxxxxxxxxx) - the free seats are limited!
Evidence-based Medical Text Simplification through Text Mining Gondy Leroy, PhD
Management Information Systems, University of Arizona
Short Summary:
To increase the health literacy of consumers and patients, tools are
needed to support writing explanatory text in a clear and understandable
manner. We use a data-driven process leveraging big data resources and text
mining to develop such a tool. This presentation will explain our corpus-based
approach, text simplification features we discovered and their impact on
comprehension.
Abstract:
It has been argued that for the Patient Protection and Affordable Care
Act to be successful, the health literacy of millions of Americans needs to
increase. Similarly, the Healthy People 2020 statement by the Department of
Health and Human Services identified improving health literacy as an important
national goal. Today, providing explanatory text is the most common approach to
educating patients. These texts need to be sufficiently simple and only one
tool is popular for simplifying text: the readability formula. Unfortunately,
there is little evidence to support a connection between its outcomes and
reader comprehension. Better tools for simplifying text are urgently needed. We
use a data-driven process leveraging big data resources and text mining to
develop such a tool. Based on corpus analysis of large corpora, e.g.,
Wikipedia, we identify text features that can be mapped from a difficult to an
easier version. We use natural language processing and external resources, e.g.
Google Web Corpus, Corpus del Espal, to develop our simplification tool. We
always conduct user testing to measure impact on perceived and actual
difficulty. Using this process, we discovered several features in English and
Spanish useful for simplification while also debunking a few myths. Term
familiarity, based on Google Web Corpus frequency, is used to identify
difficult terms that can be replaced with synonyms from sources such as the
UMLS or WordNet. Increasing term familiarity reduces perceived difficulty and
increases comprehension. Similarly, grammar familiarity, based on frequencies
of common parse tree structures, shows comparable effects and higher grammar
familiarity lowers perceived difficulty and increases comprehension. Finally,
improving coherence increases comprehension. In general, we conclude that our
process is efficient and effective to discover simplification features that
allow semi-automated text simplification with demonstrated impact.
Speaker Bio:
Gondy Leroy is Associate Professor in the Department of Management
Information Systems at the University of Arizona. She was educated at the
Catholic University of Leuven, Belgium, where she earned a combined B.S. and
M.S. in Experimental Psychology (1996) and the University of Arizona where she
earned a M.S. and Ph.D. in Management Information Systems (2003). She is an
IEEE Senior Member and serves on the editorial board of Health Systems,
International Journal of Social and Organizational Dynamics in IT, Journal of
Database Management and multiple conferences. Her research focuses on natural
language processing and text mining in healthcare. Her projects have been
funded by the Centers for Disease Control and Prevention, National Library of
Medicine/National Institutes of Health, National Science Foundation, Microsoft
Research and several foundations. She has published her work in ACM Computing
Surveys, Journal of the American Medical Informatics Association (JAMIA),
Journal of the American Society or Information Science and Technology (JASIST),
International Journal of Medical Informatics, Journal of Medical Internet
Research, and Empirical Software Engineering among others. She authored the
book Designing User Studies in Informatics, published by Springer, and conducts
tutorials on this topic in the United States, Europe, Canada and Asia. She is
active in outreach and has organized several workshops and contributed to
doctoral consortia, workshops and conferences aiming to encourage women to
enter and remain in the field of computing. She currently organizes the
Tomorrows Leaders Equipped for Diversity Program at the University of Arizona's
MIS department.
From: cochiselinux-bounce@xxxxxxxxxxxxx
[mailto:cochiselinux-bounce@xxxxxxxxxxxxx] On Behalf Of MajB
Sent: Wednesday, August 26, 2015 9:28 AM
To: cochiselinux@xxxxxxxxxxxxx
Subject: [cochiselinux] September meeting date change
Hi folks.
Due to a scheduling conflict, the date for the next Cochise Linux User
Group meeting has been moved to 16 September. The time, 5pm, and the location,
Room C165A, University of Arizona, Sierra Vista Campus, remain the same. Sorry
for the inconvenience this may cause some of you. The presentation,
Introduction to Linux, will still be given by Rex Bouwense. We are looking
forward to see you at the next meeting.
Rex
