Diesner and Mishra publish paper on NER tool for social media research

Twitter logo
Jana Diesner
Jana Diesner, Associate Professor and PhD Program Director
Shubhanshu Mishra
Shubhanshu Mishra

The identification of proper names of people, organizations, and locations from raw texts, referred to as Named Entity Recognition (NER), can be highly accurate when researchers use NER tools on a large collection of text with proper syntax. However, using existing NER tools for analyzing social media text can lead to poor identification of named entities. In particular, Twitter text frequently includes inconsistent capitalization, spelling errors, and shortened versions of words.

TwitterNER, an open-source tool developed by doctoral student Shubhanshu Mishra, who is supervised by Assistant Professor Jana Diesner, can help researchers interested in performing NER on social media text. TwitterNER has recently been shown (in an independent evaluation by Humangeo) to perform better in terms of precision than some other publicly available systems for entity types of person, location, and organization, which are often of most interest to researchers.

"Our system relies on a combination of hand-engineered features," explained Mishra. "It follows the paradigm of transductive semi-supervised learning where all the labeled and unlabeled data is utilized to make predictions about the unlabeled data."

The original implementation of TwitterNER was created for the shared-task session at the 2016 Conference on Computational Linguistics (COLING) Workshop on "Noisy User-generated Text" (W-NUT). Workshop participants were asked to build an NER system for Twitter data, which was evaluated using a common test dataset. TwitterNER had a high level of precision among the various systems.

Diesner and Mishra then improved their approach and shared it with W-NUT by submitting the paper, "Semi-supervised Named Entity Recognition in noisy-text."

"Our original submission ranked seventh in the task, but our final improved version surpassed the second-best performing system on the concluded task," said Mishra. "The winning system was based on deep learning, but its implementation is not publicly available."

Mishra has an integrated MS and BS in mathematics and computing from the Indian Institute of Technology Kharagpur. He is interested in the analysis of information generation in social networks such as those in scholarly data and social media websites. His prior projects have included systems for user sentiment profiling, active learning using human-in-the-loop design pattern, and novelty profiling in scholarly data.

Diesner is an expert in human-centered computing, network science, natural language processing, and machine learning. Recognition for her research expertise include appointments as CIO Scholar for Information Research & Technology at Illinois (2018), faculty fellow at the National Center for Supercomputing Applications (NCSA) at Illinois (2015), and as a research fellow in the Dori J. Maynard Senior Research Fellows program through The Center for Investigative Reporting and The Robert C. Maynard Institute for Journalism Education (2016). She holds a PhD from the Computation, Organizations and Society (COS) program at Carnegie Mellon University's School of Computer Science.

Updated on
Backto the news archive

Related News

Walkow selected for Mozilla Open Leaders Program

Samantha Walkow, an Informatics PhD student advised by Assistant Professor Matthew Turk, has been accepted into the Mozilla Open Leaders Program. The 14-week mentorship and project management program focuses on internet health and openness. Walkow is part of a cohort in the "culture track," in which participants learn how to design and build an open culture that promotes participation and inclusion.

Sam Walkow

Wisniewski selected as 2018-2020 iSchool research fellow

Pamela Wisniewski, assistant professor in the College of Engineering and Computer Science at the University of Central Florida, has been selected by the iSchool faculty as a research fellow for the 2019-2020 academic years. Research fellows are chosen because their work is relevant to the interests of the School's faculty and students. During the period of their appointments, fellows give at least one public lecture.

Pamela Wisniewski

Wilkin wins 2019 Hugh C. Atkinson Memorial Award

iSchool Affiliate Professor John Price Wilkin, Juanita J. and Robert E. Simpson Dean of Libraries and University Librarian, has been named the 2019 winner of the Hugh C. Atkinson Memorial Award. Wilkin will receive a cash award and citation during an ALCTS event at the ALA Annual Conference in Washington, DC.

John Wilkin

Stodden elected Member-at-Large for AAAS section

Associate Professor Victoria Stodden has been elected Member-at-Large for the Statistics section of The American Association for the Advancement of Science (AAAS). AAAS is an international, nonprofit organization dedicated to advancing science, engineering, and innovation around the world for the benefit of all people. As a Member-at-Large, Stodden will support the Statistics section's steering group in its responsibilities, which includes nominating and reviewing Fellows as well as proposing and reviewing symposia for the AAAS Annual Meeting. She will serve a four-year term, starting in February.

Victoria Stodden