Social Learning
Submissions due for review: November 7, 2009
Publication date: July/August 2010
In recent years, the social Web has shown tremendous growth, as the World Wide Web has transformed into a social platform for communication, information sharing and collaboration between Web users. Social learning is concerned with the principles, methodologies, techniques, tools, and applications of machine learning and knowledge discovery from/to social activities. A typical example is machine learning on social Web data. Several new challenges set it apart from traditional machine learning. First, the social Web allows users in different places to contribute the content at different times in an entirely decentralized fashion, resulting in multiple inconsistent and conflicting views on matters such as the different tags assigned to the same Web pages by users in social bookmark systems. Second, social Web data cover a vast number of heterogeneous entities (for example people, images, and Web pages) associated with distinct feature representations. Rich relations exist (for example, friendship and citations) among different entities. The complex nature of the data calls for relational learning algorithms for reasoning about different objects and their interactions rather than focusing on the characteristics of one set of independent homogeneous objects. Third, social activities are made by a set of human users instead of a single arbitrator, and the users usually have access to or generate only partial information. Finally, the social Web is a highly dynamic environment with new knowledge constantly emerging and evolving. Therefore, one important research issue is how to design evolutionary models that are adaptive to changes and easy to update in the online environment. This social-Web phenomenon has created an unprecedented opportunity for intelligent computing systems to leverage the power of the collective intelligence of the enormous Web user base, or the wisdom of the crowd.
This special issue will accept papers related to all aspects of learning and knowledge discovery based on the social Web. On one hand, many existing intelligent systems such as natural language processing, information retrieval and multi-agent systems can benefit from utilizing the social Web as an additional knowledge source. On the other hand, the social Web is also an emerging domain for new techniques and applications of intelligence systems. We solicit high quality research papers demonstrating challenging research issues, presenting state-of-the-art theories, techniques and showcasing successfully deployed applications. We invite submissions including, but not limited to, the following topics:
- Learning about group formation and evolution
- Social network analysis and mining
- Group interaction and collaboration
- Influence process and recognition
- Trust and reputation
- Opinion extraction and trend detection
- Expertise modeling and matching
- Multiple learner systems in social environment
- Exploitation of unannotated social Web data
- Ambiguity resolving on the social Web
- Knowledge extraction and management from social Web
- Use of the social Web data for different AI tasks
- Click log mining and user modeling
- Agent and Multi-agent system on the Web
- Model and analysis complexity
- Data collection and benchmarks
- Metrics and evaluation
- Personalization, security and privacy
Submission Guidelines
Submissions should be 3,500 to 7,500 words (counting a standard figure or table as 200 words) and should follow the magazine's style and presentation guidelines. References should be limited to 10 citations. To submit a manuscript, access the IEEE Computer Society Web-based system, Manuscript Central.
Questions?
Contact Guest Editors Qiang Yang, Nathan Nan Liu, or Zhi-Hua Zhou.