Abeed Sarker

*Notice*: I am moving this site to wordpress (easier management): https://sarkerabeed.wordpress.com/

I am currently a Research Scientist at the Institute of Biomedical Informatics of the Perelman School of Medicine, University of Pennsylvania. I am also affiliated with the Institute for Biomedical Informatics at UPenn. In addition, I serve as Honorary Research Affiliate at the Department of Biomedical Informatics, Arizona State University and the Department of Computing, Macquarie University

My current research interests include natural language processingbig data analyticscomputational linguistics, machine learning, biomedical informatics, medical informatics, and social media mining. In particular, my research is focused on solving various research problems utilizing health-related natural language.

I received my postdoctoral training at the Department of Biomedical Informatics of Arizona State University, which is located at Mayo Clinic, Scottsdale. I am particularly interested in the implementation of health systems which can learn from large unstructured data sets using supervised and unsupervised algorithms.

I completed my Ph.D in computational linguistics from the Centre for Language Technology, Macquarie University, Sydney, Australia. Prior to that, I finished my Honours in image processing, and my Bachelors in Computer Science at the same university.

Further details about my current and past research can be found in the Research page. Further research details can be found in my profiles (apologies for not compiling the information in one place; this page is an attempt to do so..).


Abeed Sarker
217 Blockley Hall 
University of Pennsylvania
423 Guardian Drive
Philadelphia PA, 19104
United States of America
Email: abeed@upenn.edu
Phone: +1-215-746-1700

Recent updates (sporadic in nature):

[March, 2017]: I presented at the CLUNCH seminar at the University of Pennsylvania on social media mining. Slides here.

[March, 2017]: Our proposed session on NLP for Precision Medicine was accepted for PSB2018. Papers are due August first. 

[December, 2016]: I am attending COLING and presenting about our tools and resources at BioTxtM. Presentation is available here.

[September, 2016]: I joined the Perelman School of Medicine, University of Pennsylvania to continue my research in health language processing. 

[June, 2016]: I organized a workshop to teach basic text classification to students from non-programming backgrounds at ASU-BMI. Notes are available here.

[April, 2016]: Interesting discussion on The Parallax about our work.

[March, 2016]: Our work on social media mining for toxicovigilance is covered in Psychiatryadvisor.

[February, 2016]: I am teaching the first half of BMI 211: Modeling Biomedical Decisions.

[January, 2016]: I gave an invited talk titled Social Media Mining for Pharmacovigilance-- progress and challenges at the Pacific Biocomputing Symposium, 2016. Proceedings for the symposium are available here. The (draft) slides are available here.

[January, 2016]: I hosted the PSB Shared Task Workshop. Proceedings available here.

[October, 2015]: I presented an overview of our work titled 'Social media mining for public health' at the Maricopa Department of Public Health. The (draft) slides are available here: http://diego.asu.edu/asarker/ma

[October, 2015]: We've received a set of very interesting systems for our social media mining shared task. 
Program and task descriptions are available here: 

[August, 2015]: Our paper Utilizing social media data for pharmacovigilance: A review got nominated for Atlas!

[June, 2015]: I am organizing the shared task on social media mining for pharmacovigilance: http://psb.stanford.edu/previous/psb16/workshop/wkshp-smm/