Social Media Mining
for Public Health Monitoring and Surveillance
At Pacific
Symposium on Biocomputing (PSB) 2016
January
4-8, 2016
The Big
Island of Hawaii
Motivation
Social networks have
seen an unprecedented growth in terms of users worldwide (e.g., as of 11th July
2014, Twitter has over 645 million users and grows by an estimated 135,000
users every day, generating 9,100 tweets per second). The social networks form
a platform for people to share, discuss, and update their views and opinions,
and many share their health-related information both in generic social media
(such as Twitter, Facebook or Instagram) and in health-related social networks
(forums focusing specifically on health issues, such as DailyStrength or
MedHelp). Advances in automated data processing, machine learning and natural
language processing present the possibility of utilizing this massive data
source for public health monitoring and surveillance, if only researchers
address the methodological challenges unique to this media.
The
use of social media for health monitoring and surveillance has indeed many
drawbacks and difficulties, particularly if done automatically. For example,
traditional NLP methods that are used on longer texts have proven to be
inadequate when applied to short texts, such as those found in Twitter.
Something seemingly simple, such as searching and collecting relevant postings
has also proven to be quite challenging, given the amount of data and semantic
heterogeneity (how people refer to the topic of interest in colloquial terms)
inherent to the media.
This session invites researchers who
are interested in automatic methods for the collection, extraction,
representation, analysis, and validation of social media data for public health
surveillance and monitoring, including epidemiological and behavioral studies.
It serves as a unique forum to discuss novel approaches to text and data mining
methods that respond to the specific requirements of social media and that can
prove invaluable for public health surveillance.
Topics of
interest include, but are not limited to:
·
Detection and
extraction of adverse drug reaction mentions in social media
·
Mapping of
disease and symptoms mentions in social media to standardized vocabularies
·
Deriving
prescription drug use and off-label use trends from social media
·
Social media in
precision medicine
·
Virus spread
monitoring using social media
·
Myths and truths
about disease discussed in social media
·
Drug abuse and
alcoholism incidence monitoring in social media
·
Prediction/detection
of abusive behavior using social media postings
·
Disease incidence
studies using social media
·
Sentinel event
detection using social media
·
Search, collection,
and analysis techniques for public health informatics using social media
·
Natural language
processing methods for health-related consumer-generated (colloquial) text
·
Classifying
health-related messages in social media
·
Sentiment
analysis of social media messages for disease surveillance
Session Organizers
Chair:
Graciela
Gonzalez (Arizona State University)
Email: ggonzalez@asu.edu
Co-Chairs:
Matthew Scotch
(Arizona State University)
Email: matthew.scotch@asu.edu
Karen Smith (Regis University)
Email:
ksmith003@regis.edu
John Brownstein (Harvard Medical School)
Email:
john.brownstein@childrens.harvard.edu
Abeed
Sarker (Arizona State University)
Email:
msarker1@asu.edu
Michael Paul (Johns
Hopkins University)
Email: mpaul@cs.jhu.edu
Azadeh Nikfarjam
(Arizona State University)
Email:
anikfarj@asu.edu
Submission Information
Please note that the submitted papers
are reviewed and accepted on a competitive basis. At least three reviewers will
be assigned to each submitted manuscript.
Important Dates
Paper
submissions due: July 27, 2015 August 3, 2015
Notification
of paper acceptance: September 14, 2015
Final
paper deadline: October 5, 2015 at 11:59pm PT
Registration
opens: August 1, 2015 at noon PT
Travel award applications
PSB has been able to offer travel
support to many attendees in the past. However, please note that no one is
guaranteed travel support.
Available:
August 1, 2015 at noon PT
Deadline: October
5, 2015 at noon PT
Decisions will be announced in
mid-October.
For details, please see http://psb.stanford.edu/keydates.html
Abstract Submissions
Poster presenters will be provided with
an easel and a poster board 32"W x 40"H (80x100cm). One poster from
each paid participant is accepted.
Available:
August 1
Deadline:
November 17, 2015 at noon PT
Decisions will be announced in
mid-October.
Paper Format
Please see the PSB paper format template and instructions at
http://psb.stanford.edu/psb-online/psb-submit.
The file formats
we accept are: postscript (*.ps) and Adobe Acrobat (*.pdf)). Attached files
should be named with the last name of the first author (e.g. altman.ps or
altman.pdf). Hardcopy submissions or unprocessed TeX or LaTeX files will be
rejected without review.
Each paper must be accompanied by a
cover letter. The cover letter must state the following:
•
The email address of the corresponding author.
•
The specific PSB session that should review the paper or
abstract.
•
The submitted paper contains original, unpublished results,
and is not currently under consideration elsewhere.
•
All co-authors concur with the contents of the paper.
Submitted papers are limited to twelve
(12) pages in our publication format. Please format your paper according to
instructions found at http://psb.stanford.edu/psb-online/psb-submit/. If figures cannot be easily resized and
placed precisely in the text, then it should be clear that with appropriate
modifications, the total manuscript length would be within the page limit.
Social Media Mining Shared Task
This year we hold
a social media mining shared task which consists of different sub-tasks related
to classification and extraction of adverse drug reaction information from
social media. More details about the task descriptions can be found here:
http://psb.stanford.edu/