Social Network Data Mining with Deep Learning Techniques
1Jinan University, Guangzhou, China
2Incheon National University, Incheon, Republic of Korea
3University of Southampton, Southampton, UK
Social Network Data Mining with Deep Learning Techniques
Description
Analysis of social networks, such as the socially connected Internet of Things (IoT), has shown the influence of intelligent information processing technology on industrial systems for smart cities. In recent years, the increased use of social networks has changed people's way of life. Compared with conventional networks, social networks have some characteristics, such as noisy, multimodal, and collective relational, which makes it a challenge to analyze, manage, and index the social media data. The automatic discovery and mining of useful information from large scale social network content and relational data for effective information search, access, and recommendation has become a key issue in the development of the internet.
Meanwhile, deep learning, which handles representation learning problems through multiple non-linear mapping, has the powerful abilities of feature learning and feature fusion. Related research shows that deep network-based models have a unique advantage in solving complex problems from massive data, and they offer potential solutions to problems in social media data mining. Feature learning, based on deep networks in social networks, aims to find representative features for social media items. It is not only an important precondition and foundation for social media information mining, but also a hot topic in multimedia and machine learning communities.
This Special Issue aims to collect research on social network data mining methods and algorithms for merging multiple sources of information by using deep learning and machine learning. Any research on modelling social network information using deep learning and machine learning methods and their application to real world social media mining problems, new aggregation approaches (not mere extensions) offered by them, and conflict/inconsistency analysis among multiple pieces of social media information are welcome. Submitted contributions that clearly delineate the role of social networks with deep learning in invited. We welcome both original research and review articles.
Potential topics include but are not limited to the following:
- Deep learning and machine learning methods for social media fusion
- Social media modeling
- Social computing
- Social media fusion systems
- Social sciences
- Social network analysis
- Social media content analysis
- Social media search
- Social recommendation systems
- Social media queries, management, and indexing
- Social media mining
- Multi-modality fusion
- Multimedia summarization, visualization, and recommendation
- Multimedia tagging and annotation
- Geo-tagged social media analysis
- Integration of social media with location data
- User behavior analysis
- Social media monetization
- Privacy and security issues