1st International Workshop on Social Media Analytics for Healthcare (SMA4H)
Il 03/12/2018 ore 09.00 - 19.00
Held in conjunction with IEEE/WIC/ACM International Conference on Web Intelligence 2018 (WI’18)
The fast expansion of social media in the last few years is making available an enormous and continuous stream of user-generated contents containing invaluable information that can be used to understand, in near real time, human life dynamics. These massive quantities of data could support a wide range of medical and healthcare applications, including among others clinical trials and decision support, disease surveillance, personalized medicines and population health management.
In the public health area, especially, physicians could take a great advantage since the available huge data can be gathered faster and at a lower cost, compared to the traditional sources, mainly surveys. The pervasiveness and crowdsourcing power of social media data allow to model phenomena that was not possible before because either too expensive or outright impossible to answer, such as distribution of health information in a population, tracking health information trends over time and identifying gaps between health information supply and demand. Besides, social media combines textual, temporal, geographical and network data, opening up unique opportunities to study the interplay between human mobility, social structure and disease transmission.
Although social media analytics research for health applications is still very much its infancy, it received a great attention along recent years. Several research studies appeared including, influenza surveillance, pharmacovigilance, user behavioral patterns, drug abuse, depression, well-being, assisted living and tracking infectious/viral disease spread.
Aims and Topics
Big data analytics applications take advantage of such an explosion in social data to extract insights for improving healthcare. Social media data can be mined to obtain patterns and knowledge that can be leveraged in descriptive as well as predictive models of population health. By discovering associations and understanding patterns and trends within the data, big data analytics has the potential to improve the overall effectiveness of public health monitoring and analysis and significantly reduce its latency and costs.
The First International Workshop on Social Media Analytics for Healthcare (SMA4H) provides a venue to promote collaborations, present and exchange ideas, practices and advances specific to social media use in the particularly challenging area of health applications. It brings together individuals representing academia, public health researchers and practitioners and provides a forum for dialogue within and across different disciplines in the field of Web Intelligence: collective intelligence, data science, human-centric computing, knowledge management, network science, social network analysis, machine learning, statistical modelling, computational linguistics, epidemiology, sociology, and public health research. The workshop is an excellent opportunity to shape the future of health delivery, communication and practice by discussing novel approaches to big data analytics and mining methods that are applicable to social media data and may prove invaluable for health monitoring, surveillance, disease spreading and outbreaks prediction.
The workshop solicits empirical, experimental, methodological, and theoretical research reporting original and unpublished results on social media analysis and mining on topics in the realm of healthcare and health informatics along with applications to real life situations. This can mean new models, new datasets, new algorithms, or new applications.
Topics of interest include, but are not limited to:
Crowdsourcing of network health data
- Methods for the automatic detection and extraction of health-related concepts
- Data pre-processing and cleansing to deal with noise and missing data
- Classifying and clustering of temporal health data in high dimensional spaces
- Application of deep learning methods to health data
- Novel architectures for scalable health data analysis and mining
- Statistics and probability in large-scale health social data analysis
- Community discovery and analysis
- Large-scale graph algorithms for social network analysis
- Social geography and spatial networks
- Mobility mining
- Spatio-temporal health data mining
- Spatio-temporal prediction of pandemics
- Methods for capturing outbreaks of infectious diseases
- Modeling the health status and well-being of individuals
- Models to predict the users’ moods from social posts
- Real-time syndromic surveillance and early detection of emerging disease
- Virus spread monitoring and modeling
- Detect health-related topics of discussion and events
- Drug abuse and alcoholism incidence monitoring
- Methodologies and measures to understand patterns and trends for general public health research
- August 31, 2018: Paper Submission deadline
- September 28, 2018: Paper Notification
- October 12, 2018: Camera-Ready Paper Due
- December 03, 2018: Workshop
Submitted papers must be unpublished and not considered elsewhere for publication. Submissions will undergo a rigorous review process handled by the Technical Program Committee. Papers will be selected based on their originality, significance, relevance, and clarity of presentation. Only electronic submissions in PDF format through the workshop submission site will be considered. Papers must be in English, up to 4 pages in the IEEE conference proceedings format, including references. The IEEE Proceedings Manuscript Formatting Guidelines can be found at: https://www.ieee.org/conferences/publishing/templates.html
At least one of the authors must register and present the paper, if accepted. Registered and presented papers will be included in the Workshop Proceedings published by IEEE. They will also be invited to be expanded and submitted for possible publication in an International Journal special issue.
- Carmela Comito, Cnr Institute of High Performance Computing and Networking (Cnr-Icar)
- Agostino Forestiero, Cnr Institute of High Performance Computing and Networking (Cnr-Icar)
- Clara Pizzuti, Cnr Institute of High Performance Computing and Networking (Cnr-Icar)
- Leopoldo Bertossi, Carleton University, Ottawa, Canada
- Stefano Cagnoni, University of Parma, Italy
- Andrea Calì, University of London, United Kingdom
- Mario Ciampi, National Research Council (ICAR-CNR), Italy
- Anne Laurent, LIRMM, University of Montpellier, France
- Corrado Loglisci, University of Bari, Italy
- David Manset, GNUBILA/MAAT, France
- Monica Mordonini, University of Parma, Italy
- Mehdi Sheikhalishahi, InnoTec21 GmbH, Germany
- Paolo Trunfio, University of Calabria, Italy
- Ester Zumpano, University of Calabria, Italy
CNR - Istituto di calcolo e reti ad alte prestazioni
Via Pietro Bucci, cubo 8/9C Rende (CS) - 87036
Modalità di accesso: a pagamento