Abstract:
The Web has shifted from a read-only medium where most users were solely consumers of information, to an interactive medium where collaborative technologies allow anyone to publish or edit content. In this environment, social media such as social network sites, blogs, wikis, and content-sharing websites have flourished and now masses of users are contributing to the pool of human knowledge that is the Web. This large-scale user participation means that the content-creation capacity of the Web has exploded and there is now wide coverage of news, niche interests and hyperlocal content, all available in real-time. In short, Web 2.0 services have successfully harnessed collective intelligence and a huge and diverse information source has emerged.
The downside of social media as an information source is that often the individual items are very short, informal and lacking in metadata. Despite the wealth of information available in online communities, locating objects of interest can still be challenging. The search and navigation of social media could be greatly improved by augmenting the content of social media items with annotations to provide additional context or descriptors.
This thesis investigates the potential of using related data from the Web to enrich social media items with metadata and thus make it easier to find or browse information in social media. We provide three methods by which social media items can be augmented with novel metadata, specifically tags, locations and categories. Our approaches make use of existing Web data retrieved from HTML documents, APIs and Linked Data. We describe how Semantic Web technologies can be used to represent social media posts and their metadata in a uniform way and thus allow enhanced search and browsing over online community data integrated from heterogeneous sources.
