Zhai ‘s research spans several related fields including information retrieval, natural language processing, machine learning, data mining, and bioinformatics. His primary research interest is developing techniques for managing and exploiting large amounts of text information, such as news articles, email messages, scientific literature, government documents, and all kinds of Web pages.
“With the dramatic growth of online information, we are overwhelmed with huge amounts of information and have an urgent need for powerful software tools to help manage and make use of it,” explains Zhai. “I work on a variety of general techniques for searching, filtering, organizing, and mining text information and develop applications in multiple domains including Web, email, and literature.”
Zhai and his team are tackling the problem from a variety of angles, from personalized search, to text mining and information retrieval solutions that better enable task support and decision making capabilities.
Personalized Search Solutions
One of the projects that Zhai is working on is User-Centered Adaptive Information Retrieval (UCAIR), which currently works with the Yahoo! search engine. The software is able to learn what you are interested in and pushes out the recommended information the next time you search.
“UCAIR naturally optimizes search results for you and learns your search history and observes how you search”, says Zhai.
“For instance, if a user types in the word 'jaguar,' a series of search results are going to appear. If the user clicks on the 'car' search results, the software saves the information and pushes away the animal search results the next time the user searches for 'jaguar',” Zhai added.
Professor Zhai currently partners with Surf Canyon, a technology company that uses semantic real-time implicit personalization to improve search result relevancy. The technology, developed initially in Zhai’s lab, works by re-ranking search results “on the fly” based on a user model generated from real-time selections. The primary goal is to use more user information to assist the user in finding relevant information that's buried within the often overwhelming amount of search results. Zhai and his students continue to work with Surf Canyon to extend the technology and develop new features.
Zhai is also working on a search application and a mining application that will help people manage and explore textual information. With his Information Access project, users are connected to useful information at the right time.
Information Access is implemented as a personal search agent that sits on the client-side. The system integrates information around a user, rather than around a source as is common with most search engines. In this way, the system and the user are able to collaborate with each other, going beyond search toward task support.
Aiding Decisions
Zhai’s work in text mining is aimed at helping users harness information in order to make decisions. Text mining is used on websites such as eBay and Amazon to assist users in finding items they wish to purchase, among other activities. Zhai is working on a text mining application that uses opinion integration, aligning opinions together to help people make decisions.
As an example of this work, Zhai and his students have developed a news recommender application on Facebook. Facebook users register a community by providing a keyword description and a set of news sources. The system then fetches the news articles and filters them based on the community description to prepare daily news digest.
Another project Zhai is working on is a Topic Map, which is used to guide a user in navigating in the information space. The topic map constructs a map to guide the user when they are lost and don’t know the destination.
“The Topic Map allows users to view pages people have viewed as information foot prints, such as what pages get clicked. It organizes the foot prints as a map so future users can follow previous users foot prints. More users means more effective browsing”, Zhai explained.
Ideally, Professor Zhai wants the UCAIR and Topic Map projects to work together, so users can know what they like and what they have skipped in the past.
_______________
Contact: ChengXiang Zhai, Department of Computer Science, 217/244-4943.
Jennifer LaMontagne, associate director of communications, Department of Computer Science, 217/333-4049.
Writer: Kymberly Burkhead-Dalton.
If you have any questions about the College of Engineering, or other story ideas, contact Rick Kubetz, Engineering Communications Office, 217/244-7716, editor.