Jump to Main Content
Jump to Top Navigation
Jump to Footer Navigation
University of Washington

University of Washington Information School

  • Programs
    • Informatics Undergraduate major and minor
    • MLIS Master of Library and Information Science
    • MSIM Master of Science in Information Management
    • Museology Master of Arts
    • Ph.D. Doctorate Program
    • Professional & Cont. Ed. Related programs & non-degree options
  • Research
    • Research Impact How our research drives progress and helps people
    • Updates The latest news from our faculty and research staff
    • Research Areas Core topics of iSchool research
    • Research Groups Hubs for innovative scholarship & research
    • Grants & Awards Recent funding for iSchool research projects
  • News & Events
    • News The latest stories from our community
    • Events What's happening on campus and beyond
    • Podcast Documents That Changed the World, with Joe Janes
  • People
    • Directory Find iSchool faculty, staff and students
    • Alumni Stay connected with the iSchool and fellow alumni
    • Advising & Support Find help from our team of student advisors
    • Faculty Affairs Making the iSchool a joyful professional community for faculty
    • I Am the iSchool Meet some of our students and alumni
  • The School
    • About Us The iSchool is home to innovators and leaders who make information work
    • Diversity We are committed to building an inclusive community
    • Employers & Partners How to collaborate with faculty and students
    • Capstone Students work with organizations to solve information problems
    • Support the iSchool Every gift makes a difference to students
Request Information
Information Tools
Search Menu
banner image

Research

Constructing and evaluating automated literature review systems

Automated literature reviews have the potential to accelerate knowledge synthesis and provide new insights. However, a lack of labeled ground-truth data has made it difficult to develop and evaluate these methods. We propose a framework that uses the reference lists from existing review papers as labeled data, which can then be used to train supervised classifiers, allowing for experimentation and testing of models and features at a large scale. We demonstrate our framework by training classifiers using different combinations of citation- and text-based features on 500 review papers. We use the R-Precision scores for the task of reconstructing the review papers’ reference lists as a way to evaluate and compare methods. We also extend our method, generating a novel set of articles relevant to the fields of misinformation studies and science communication. We find that our method can identify many of the most relevant papers for a literature review from a large set of candidate papers, and that our framework allows for development and testing of models and features to incrementally improve the results. The models we build are able to identify relevant papers even when starting with a very small set of seed papers. We also find that the methods can be adapted to identify previously undiscovered articles that may be relevant to a given topic.

Read the full article from Scientometrics.

Jason Portenoy

Jevin D. West

Back to main page

Projects in Data Science

  • Automated Literature Review
  • FlashSciTalks: Carole Palmer
  • What Makes People Join Conspiracy Communities? Role of Social Factors in Conspiracy Engagement
  • Public Libraries and Open Government Data: Partnerships for Progress
  • What Makes People Join Conspiracy Communities?: Role of Social Factors in Conspiracy Engagement
  • Constructing and evaluating automated literature review systems
  • Cross-disciplinary data practices in earth system science: Aligning services with reuse and reproducibility priorities
  • Election Integrity Partnership

News

25 years in, Information School is more essential than ever

Tuesday, October 14, 2025
Twenty-five years ago, there were no smartphones or social media. Most of us had dial-up internet. We went to Blockbuster when we wanted to rent movies and read newspapers when we wanted to stay informed. Artificial intelligence was the...
Read more
A photo of Cynthia Leitich Smith and images of two of her books, "Jingle Dancer" and "Sisters of the Neversea."

Cynthia Leitich Smith to share insights on Indigenous stories

Wednesday, October 8, 2025
Children's and young adult book author Cynthia Leitich Smith writes stories that center Indigenous youth as heroes. Her storytelling draws inspiration from moments and experiences she’s had in her own life.“I didn't really think of it...
Read more

Events

Oct 17
 
12:00-1:00PM

iSchool Virtual Panel Series: Positioning Yourself for Success: Career Advice for the Evolving Job Landscape

Oct 17
 
4:00-5:00PM

Informatics Program Overview for Future UW Seattle First-Year and Current High School Students

Zoom / Online
Oct 22
 
12:30-1:30PM

Level-Up Your LinkedIn

Mary Gates Hall 224
Oct 22
 
4:30-5:30PM

IUGA Fall 2025 Town Hall

Zoom/Online
iSchools.org
  • Jobs
  • Contact Us
  • Privacy Policy
  • Terms & Conditions
  • Logo & Brand Guidelines
  • IT / Help Desk
  • Bluesky
  • Facebook
  • Instagram
  • Youtube
  • LinkedIn
Make a Gift
iSchools.org
© 2025 UW Information School
Box 352840 - Mary Gates Hall, Ste. 370
Seattle, WA 98195-2840
United States of America
206-685-9937
Close menu
Toolkit
Request Information

Search:

All People
  • Programs
    • Informatics
    • MLIS
    • MSIM
    • Museology
    • Ph.D.
    • Professional & Cont. Ed.
  • Research
    • Research Impact
    • Updates
    • Research Areas
    • Research Groups
    • Grants & Awards
  • News & Events
    • News
    • Events
    • Podcast
  • People
    • Directory
    • Alumni
    • Advising & Support
    • Faculty Affairs
    • I Am the iSchool
  • The School
    • About Us
    • Diversity
    • Employers & Partners
    • Capstone
    • Support the iSchool

toolkit

  • iSchool Intranet
  • MyUW
  • Outlook on the web
  • Office 365
  • Workday
  • UW Time Schedule
  • UW Academic Calendar
  • Knowledge Base
  • Watermark
  • Azure Dev Tools
  • Canvas LMS
  • Qualtrics
  • Emergency Info
  • Site Login
Loading Results...Loading search results, please wait.

Highlights

Full Results

See Full Results
See Full Directory

Customize Your Experience

  • Future Students
  • Current Students
  • Faculty & Staff
  • Everyone