Organization of Knowledge and Information Subscribe to Organization of Knowledge and Information

RELATED RESEARCH PROJECTS

1824234195_e6b913c563_z
Google

Microblogging services like Twitter are becoming an important part of how many people manage information in their day to day activities. As microblog traffic increases (Twitter currently sees about 50 million tweets per day) information management and organization will become keen problems in this area. The project will define the core problems in microblog search and propose solutions to these challenges in the form of both theoretical models and prototype search systems.

 

rare-book-text
Google

In order for older texts to be searchable, contemporary English needs to be translated into language from various historical timeframes. The project will develop software that will let people enter a query in contemporary English, and search over English texts throughout history—from Medieval times to the present day. The project will mostly involve training statistical models that assign probabilities of the translation to a word or phrase in a target English language. The project will also look at how to display results in order to provide the user with the most probable answer to the query.

1024px-insect_safari_-_beetle_24a
National Science Foundation

Taxonomists are scientists who describe the world’s biodiversity. These descriptions of millions of species allow scientists to do many different kinds of research, including basic biology, environmental science, climate research, agriculture, and medicine. The problem is that describing any one species is not easy. The language used by taxonomists to describe their data is complex, and typically not easily understandable by computers nor even other scientists. This situation makes it harder to search for patterns across millions of species documented by thousands of researchers over many decades of work worldwide.

The goal of this research is to help researchers develop and use relatively simple tools to describe species in a way that make those descriptions easier to share...

6123892769_1befc31f38_o
Intelligent Medical Objects

Diesner’s team is developing a natural-language processing solution for probabilistic entity detection and classification in the domain of healthcare. The core of the solution are prediction models built by using supervised and/or semi-supervised machine learning techniques. The resulting models can be used to annotate natural language text data documents for entity classes. The team will perform fact extraction from medical text data documents as well as map tokens to predefined medical codes. Both tasks involve the same steps: 1) building and evaluating prediction models, 2) helping to integrate the prediction models into IMO’s workflow, 3) building an inference engine for practical applications, 4) building a technical solution with which IMO can update the prediction models, and 5...

veteransaffairs
U.S. Department of Veterans Affairs

iSchool faculty members Catherine Blake and Michael Twidale are working as expert advisors to the US Department of Veterans Affairs (VA) Information Resource Center (VIReC) on a project to analyze the socio-technical aspects of VA’s HSRData-L Listserv. VIReC is a VA Health Service Research & Development Service (HSR&D) resource center that supports VA researchers in need of information about data resources specific to their research. HSRData-L is a virtual community of VA researchers who share their collective knowledge and experience about VA data and information systems for the betterment of research focused on Veteran’s issues. The team is led at the VA by Maria Souden, VIReC associate director for communications. iSchool doctoral student Caryn Anderson, who has worked...

IN THE NEWS

Aug. 1, 2017
jodischneider-sq

Assistant Professor Jodi Schneider will serve as a keynote speaker for the eighth annual VIVO Conference, which will be held August 2-4 in New York City. VIVO is member-supported, open-source software and an ontology for representing scholarship. Hundreds of universities around the world are using VIVO software to showcase the experts, publications, and impact of researchers in academic institutions.

The international conference brings together the VIVO community and its partners to share the latest developments in Semantic Web academic profiles. Schneider will give the keynote, "Viewing universities as landscapes of scholarship."

Abstract: The university can be seen as a collection of individuals, or as an administrative engine, but what sets a university apart is the production of knowledge and knowledgeable people, through teaching, learning, and scholarly inquiry. In 2000, Michael Heaney proposed that the...

Jul. 14, 2017
dalejoseph-sq_0

An interest in organization led Dale Josephs to the field of library and information science and his current job at eBay. Josephs uses the skills he learned at the iSchool—cataloging, metadata, Python programming, and data mining—to develop new analytics tools.

Where do you work and what is your role?

As a taxonomy designer at eBay, I not only act as a traditional cataloger, placing content under the appropriate category headings, but I also evaluate and edit the categories themselves. The task is equal parts content analysis and psychology. I need to ensure that the categories don't get subdivided more deeply than the site can handle and that the category structures accurately reflect where people coming to the site would expect to find these things, while ensuring that as much site content...

Nov. 8, 2016

Associate Professor Kathryn La Barre has been invited by the Knowledge Organization Research Group (KOrg) to work with doctoral students and faculty in the School of Information Studies at the University of Wisconsin, Milwaukee. On November 10, she will deliver an invited talk titled, "Interrogating Facet Theory: Decolonizing KO," which will address the following:

Current online search and discovery systems instantiate search filters (often called facets) to intuitively support searchers as they refine queries and review result sets. Facet analytical theory was promoted by S.R. Ranganathan as a reaction against earlier approaches to knowledge organization, such as the Dewey Decimal Classification, that consider knowledge as an integral whole that can be divided into smaller and more discrete units in...

Oct. 7, 2016

Assistant Professor Vetle Torvik has been named the iSchool's Centennial Scholar for 2016-2017. The Centennial Scholar award is endowed by alumni and friends of the School and given in recognition of outstanding accomplishments and/or professional promise in the field of library and information science.

Torvik expressed surprise and gratitude at receiving this honor. "I am in awe of colleagues who received it before me; their caliber is off the charts," he said. "I hope to use the award to open new doors—a stamp of approval from colleagues who know you well goes a long way to establish new collaborations necessary to solve the increasingly complex problems facing science and society today.”

Torvik joined the faculty in 2011. His current research addresses problems related to scientific discovery and collaboration using complex models and large-scale bibliographic databases. He is the author of articles in journals such as Proceedings of the National Academy of...

Sep. 9, 2016

The iSchool is pleased to announce that Matthew Turk has joined the faculty, effective September 9. Assistant Professor Turk holds a joint appointment with the Department of Astronomy in the College of Liberal Arts and Sciences. His work focuses on how individuals interact with data, and how that data is processed and understood. 

"We are very excited that Matthew Turk is joining us," said Dean Allen Renear. "Matt is a truly extraordinary researcher in data science who also embodies the commitment to interdisciplinary education that is at the heart of our School. A recipient of the prestigious Gordon and Betty Moore Foundation’s Moore Investigator Award in Data-Driven Discovery, Matt is already a leading figure in his field."

Turk's research areas include the organization of and meaning behind data, how groups of individuals collaborate in an inherently competitive system, and how the interaction of software and the human experience of knowledge generation can be...

Jul. 27, 2016

Doctoral student Jacob Jett, faculty affiliate Timothy W. Cole, Research Associate Professor David Dubin, and Professor and Dean Allen H. Renear will present, “Discerning the intellectual focus of annotations,” at Balisage: The Markup Conference 2016.

Abstract: Much attention has been given to strategies for anchoring annotations in digital documents, but very little to identifying what the annotation is actually about. We may think of annotations as being about their anchors, but that is not typically the case. Two annotations may have the same anchor, such as a string of characters, but one annotation is about the sentence represented by that string and the other about the claim being made by that sentence. Identifying targets and making this...

Jul. 13, 2016

Associate Professor Miles Efron will participate in the 39th International Conference of the Association for Computing Machinery (ACM) Special Interest Group on Information Retrieval (SIGIR). The conference will be held July 17-21 in Pisa, Italy.

Efron and his doctoral students Craig Willis and Garrick Sherman will present the short paper, “What Makes a Query Temporally Sensitive.”

From the abstract: This work takes an in-depth look at the factors that affect manual classifications of “temporally sensitive” information needs. We use qualitative and quantitative techniques to analyze 660 topics from the Text Retrieval Conference (TREC) previously used in the experimental evaluation of temporal retrieval models. Regression analysis is used to model previous manual classifications. We identify factors and potential problems with previous classifications, proposing principles and guidelines for future work on...

Pages