Skip to content


General Contact Information

 

Phone: 646-660-6500

Fax: 646-660-6501

 

Email:

provost.office@baruch.cuny.edu

 

Mailing Address:

Office of the Provost & Senior Vice President for Academic Affairs

Baruch College/CUNY

One Bernard Baruch Way
Box D-701

New York, NY 10010-5585

 

Walk-In Address:

Administrative Center

135 East 22nd Street, 7th Floor

Office of the Provost and Senior Vice President for Academic Affairs

Message Archive



Monday, November 2, 2015

 

This email is being sent to all members of the Baruch College faculty.

For an archive of announcements sent from the Associate Provost beginning June 2011, click here.

 

Analytics Seminar:

Gondy Leroy (University of Arizona)

Tuesday, November 10, 12:45-2:15pm, NVC 14-280

 

From: Professor Radhika Jain, Computer Information Systems

Our second speaker of the semester in the Analytics Seminar Series is Professor Gondy Leroy from the 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 and the 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 Español, 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 (JMIR), 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. Since 2013, she has led the Tomorrow’s Leaders Equipped for Diversity program at the University of Arizona’s MIS department.

 

For more information, please contact Prof. Radhika Jain at Radhika.Jain@baruch.cuny.edu