There is a huge amount of data generated in social computing and it contains various types of data. The huge data size, variety, velocity, accuracy and high dimensionality of data present new challenges including noise, privacy, scalability, correlation, incidental endogeneity and measurement errors. This big social data has evolved as a most challenging field of study and research area. It has drawn much attention during the last few years and influences our modern society business, government, healthcare and research in almost every discipline.
Existing approaches to big social data analysis mainly rely on parts of text in which sentiment is explicitly expressed. The social media feeds, blogs, emails, forums, survey, corporate documents, news, and call centre logs are textual data to be analysed. In last decade, social media has emerged as an area of scientific analysis. The sentiment analysis is a new type of text analysis technique to determining the opinion and subjectivity of reviewers. However, opinions and sentiments are often conveyed implicitly through latent semantics, which makes a purely syntactical approaches ineffective.
We will focus on the mathematical aspects, modelling, storage management, computing, and applications of novel techniques that further develop and apply effective social computing tools and techniques for big social data analysis. A key motivation for this special issue, in particular, is to explore the adoption of novel effective big social data computing frameworks and machine learning systems to go beyond a mere word-level analysis of structured, semi- structured and unstructured data, in potentially any domain.
We aim to provide a leading opportunity for researchers, academicians, professionals and developers from different background areas to exchange the latest research ideas and synergic research and development on fundamental issues and applications about big data and social computing analysis.
Suitable topics include, but are not limited, to the following:
- Mathematical aspects and applications of big data and social computing
- Big data in social computing
- Social network modeling and analysis
- Social media representation and retrieval
- High performance computing in big data and social computing
- Intelligent social media
- Implementing big data architectures
- Big data analytics and storage
- Data mining and knowledge discovery
- Data mining in healthcare
- Support vector machines
- Web-usage mining, and text and image recognition to prominent applications
- Big data programming models and platforms: MapReduce or spark for big data
- Social computing for mobile big data
- Pattern recognition and image processing
- Machine learning
- Sentiment analysis
- Social cloud computing
- Security and privacy in big data
- Data visualization
Submission of manuscripts: 1 January, 2017
Notification to authors: 1 February, 2017
Final versions due: 1 March, 2017