Outreach: Women in Computing
Semantic Search Engines
Complete System Examples of Search Engines
MedTextus: A meta-search engine that uses Intelligent interfaces. Comparison studies were done between MedTextus, HelpfulMed, and NLM Gateway to evaluate query expansion tools (manual) and results overview tools (visualized clustering and lists).
GeNetscene: Access to biomedical text, a search engine that incorporates a text mining approach.
Resources for Search Engine Development
Parsing triples from text. See GeNetscene for demo. Download medical lexicons for parser tagging.
Search Engine Augmentations: Difficulty Levels of Retrieved Text
Millions of people read health information online but many lack understanding of this information. Such misunderstanding of health information increases the number of unwise decisions and leads to poorer health and higher healthcare costs. Even a small improvement in readers' understanding will have a significant impact because it may lead to fewer unwise decisions. This project undertakes the first steps necessary to learn which simplifications and transformations in medical text increase consumer understanding. Our goal is to find structures in text, new or previously found by others to be associated with understanding. If successful, this project will lead to the development of a metric that reflects text characteristics associated with comprehension difficulties and the development of an "intra-lingual machine translation" program to move from difficult to easier-to-understand text.
Search Engine Augmentations: Visualization of Retrieved Text
Research indicates that the text on many popular web sites is difficult to understand and consumers find that reading documents in electronic format is problematic. Since health information read online influences the patient-doctor relationship - e.g., treatments requested, or perceived patient value from a doctor's visit - it is important that this information be interpreted and remembered as completely and correctly as possible. Misunderstandings in health information may increase the risk of making unwise health decisions, which could lead to poorer health and higher health care costs. The goal of the project is to develop and test new technology that can present online health information that is easier to understand and remember. Prototypes will be developed that will visualize both the structure and content of web pages to increase understanding and retention without oversimplification. A small pilot study has shown positive effects of such a representation. The two prototypes will differ in how much content detail is included in the visualization. They will be evaluated for their effects on understanding and retention of information and compared with currently existing web sites. User behavior and preferences will also be captured and analyzed. Three user groups will participate in the development and evaluation of the prototypes: elderly consumers, Hispanic non-native speakers, and patients. These groups were chosen for their specific characteristics (age related problems, sub-optimal command of English, and patients' stress) that may require improved information presentation.
Automated Interviewing of Witnesses of Crimes
The purpose of this project is to research the need, impact, and feasibility of collecting unreported crime via the Internet. We are developing a prototype, online submission system that can be used to collect unreported crime data. This Internet-based submission system will give crime victims and witnesses the advantage of anonymity, convenience, the possibility to use different data formats (video, pictures, text) and different access methods (via computer or cell phone). The system will analyze reported data to generate information needed by law enforcement officers. With this information, officers will follow up on crime reports and will be able to better allocate resources.
Assisted Communication using Mobile Devices
Autism has been increasing in the U.S. at a staggering rate. Autism is characterized by developmental disabilities, extreme withdrawal, lack of social behavior, severe language and attention deficits, and repetitive behaviors. Autistic children often use pictures, such as the Picture Exchange Communication System (PECS), to communicate. We have created open source software, PixTalk, that can be used in the same manner as PECS. The software can be used on smartphones and PDAs that run a Microsoft Operating System and is available free of charge. In addition, we also provide a set of images that can be used with the software and that are also free of charge and not copyrighted.
Note: Testing of the software has started with children with autism. If you are interested in participating, please contact Gondy Leroy)
[Project Details] [Software downloads and Online Community] [Watch Video]
Last updated: 09/11/2009