The Social Media Mining for Health Applications (#SMM4H) Shared Task involves natural language processing (NLP) challenges of using social media data for health research, including informal, colloquial expressions and misspellings of clinical concepts, noise, data sparsity, ambiguity, and multilingual posts. The proceedings of the shared task will be presented at the 6th SMM4H Workshop hosted by NAACL (North American Chapter of the Association for Computational Linguistics). This year’s shared task has eight NLP challenges, the most hosted at SMM4H.
For each of the eight tasks listed below, participating teams will be provided with a set of annotated tweets for developing systems, followed by a three-day window during which they will run their systems on unlabeled test data and upload it to Codalab. For additional details about the tasks and information about registration, data access, paper submissions, and presentations, go to https://healthlanguageprocessing.org/smm4h-shared-task-2021/
For information regarding workshop paper submissions, topics and deadlines to the workshop go to https://healthlanguageprocessing.org/smm4h-2021/
This year’s SMM4H Shared Task features tasks across text classification, named entity recognition (NER) and entity normalization problems on social media datasets. Researchers will have the opportunity to apply state-of-the-art methods on multiple tasks to further validate your research on data from social media. For students and educators, this is an excellent opportunity to teach and apply natural language processing (NLP) techniques by participating in the shared tasks. Each participating team will have the opportunity to submit a 2-page system description which will be published as part of the shared task proceedings.
This year’s shared tasks are listed below. If you are interested in one or more of these tasks, please register your team at : https://forms.gle/1qs3rdNLDxAph88n6
1) Classification, Extraction and Normalization of Adverse Effect mentions in English tweets : https://healthlanguageprocessing.org/smm4h-2021/task-1/
2) Classification of Russian tweets for detecting presence of Adverse Effect mentions
https://healthlanguageprocessing.org/smm4h-2021/task-2/
3) Classification of change in medications regimen in tweets
https://healthlanguageprocessing.org/smm4h-2021/task-3/
4) Classification of tweets self-reporting adverse pregnancy outcomes
https://healthlanguageprocessing.org/smm4h-2021/task-4/
5) Classification of tweets self-reporting potential cases of COVID-19
https://healthlanguageprocessing.org/smm4h-2021/task-5/
6) Classification of COVID19 tweets containing symptoms
https://healthlanguageprocessing.org/smm4h-2021/task-6/
7) Identification of professions and occupations (ProfNER) in Spanish tweets
https://healthlanguageprocessing.org/smm4h-2021/task-7/
8) Classification of self-reported breast cancer posts on Twitter
https://healthlanguageprocessing.org/smm4h-2021/task-8/
Important dates for shared tasks:
Training set release : Dec 15, 2020
Codalab link available : Feb 1, 2021
Validation set submission due : Feb 15, 2021
Test set release : Feb 26 – Mar 1, 2021
Test set predictions due : Mar 1 – Mar 4, 2021
Test set evaluation scores release : Mar 8, 2021
System descriptions due : Mar 15, 2021
Acceptance notification : Apr 1, 2021
Camera ready system descriptions : Apr 12, 2021
Workshop : June 10
Organizers:
Graciela Gonzalez-Hernandez, University of Pennsylvania, USA
Arjun Magge, University of Pennsylvania, USA
Davy Weissenbacher, University of Pennsylvania, USA
Ari Z. Klein, University of Pennsylvania, USA
Karen O’Connor, University of Pennsylvania, USA
Abeed Sarker, Emory University, USA
Mohammed Ali Al-Garadi, Emory University, USA
Elena Tutubalina, Kazan Federal University, Russia
Zulfat Miftahutdinov, Kazan Federal University, Russia
Ilsear Alimova, Kazan Federal University, Russia
Martin Krallinger, Barcelona Supercomputing Center, Spain
Juan Banda, Georgia State University, USA
Contact Information:
Arjun Magge (Arjun.Magge@pennmedicine.upenn.edu)