Business challenge

Institute of Cognitive Science at Osnabrück University researchers saw that social media held many potential clues and needed a way to effectively analyze the content and form predictions.

Transformation

In only six months, researchers were able to develop a NLP system that analyzes Twitter feeds against a central body of knowledge to help predict flu outbreaks and even answer user questions.

Results

60% of research time saved

by letting researchers code and implement software faster to focus more time on conceptual issues

2 weeks saved for updates

by instantly examining real-time data rather than waiting for delayed data from hospitals

Generates commercial interest

by building predictive capabilities that can serve the healthcare and health insurance industries

Business challenge story

Business challenge

Cognitive science is an academic field that studies mental processes, and its research has led to key findings about artificial intelligence, cognitive disorders and more. Osnabrück University is home to an Institute of Cognitive Science that traditionally seeks out important projects to serve society while reinforcing the university’s reputation among scholars and supporters. The institute’s research spans academic disciplines, provides unprecedented opportunities for research students and successfully attracts third-party funding. In 2015, the institute conceived of a research project to predict and manage flu outbreaks. The institute knew it would need to consider a wealth of data and wanted a system that could find clues within free-form discussions on social media, even advising people about the precautions they needed to take.

“Within only six months, our students have been able to implement a project that is commercially relevant.”

—Professor Dr. Gordon Pipa, Chair of the Neuroinformatics Department, Osnabrück University

Transformation story

Cognitive transformation

The institute’s new system at Osnabrück University examines approximately 500 million English tweets worldwide every day, using IBM® Bluemix® technology and the IBM Watson™ Developer Cloud to access the IBM Watson Natural Language Classifier service. The solution studies nuances in the content and context of tweets, discerning whether someone is discussing the flu vaccine or flu-like symptoms. Then, the system finds correlations between the discussions and flu outbreak factors in its central body of knowledge that includes more than 3,000 research papers and data from the Centers for Disease Control and Prevention (CDC) in the US. Based on these correlations, the system can help predict outbreaks before they happen. It can also pair its knowledge with IBM Watson Engagement Advisor technology to answer free-form questions such as “Is there a flu threat in this neighborhood?” or “Do I need to be vaccinated?” The solution took only six months to develop and improves its responses to questions over time. Once distributed beyond the institute, the system has significant potential to impact healthcare and health insurance with outbreak predictions that help facilities stock medications or take actions to reduce the severity and spread.

Results story

Quantifiable benefits

With the new solution, the Institute of Cognitive Science at Osnabrück University saved two-thirds of its software development time, gaining much more time for conceptual work. By analyzing live social media content against research reports, the system removes the two-week delay for hospital data and drives instant analysis that can help predict outbreaks and offer relevant precautions.

Osnabrück University accelerated research by 60 percent and developed commercial capabilities by generating flu outbreak predictions based on analyzing social media and research reports with an IBM Watson Natural Language Classifier system. The solution is the first of its kind in Europe and helps solidify Osnabrück as the leading German university in cognitive science.

Before the institute employed cognitive technology, its researchers had to try to perform predictive analysis on hospital data that was two weeks old by the time they received it. Now, researchers can perform predictive analysis based on 500 million live tweets per day, weighed against more than 3,000 of the latest research papers and data from CDC.

The system analyzes 500 million English tweets per day, along with a central body of knowledge that includes more than 3,000 complete research papers and data from CDC. Researchers are also loading new data from state agencies and hospitals.

About Osnabrück University

Located in Osnabrück, Germany, Universität Osnabrück, or Osnabrück University in English, specializes in research and teaching for the humanities, social sciences, cognitive science, law, and business administration and economics. Founded in 1974, the university has around 13,500 undergraduate, graduate and PhD students.