Social media services, such as YouTube, Flickr and Slideshare, contain enormous number of content valuable for education. If the requested theme can be effectively searched or recognized, teacher can easily construct the course material from social media sources. However, the search engines are not optimal for educational purposes: Search engines can list numerous pieces of content that matches more or less perfectly to keywords. After search there are thousands of pieces of content to check manually if they really fit to the requested subject. Recently, e.g. Google had added semantics into its searches, but many educational subjects require more detailed conceptual models for successful content personalization.
A common method to increase information accessibility in social media applications is tagging. However, when tags are used only as single words, we easily end up to information overload. Furthermore, in social media, we do not have standardized way to tag content. In fact, tagging the content in an optimal way is a difficult task for several reasons: Cultural background, educational background, community and its social behavior, as well as context1 where tagging is constructed affects enormously to the selection of tags. Tagging is very subjective and more research is needed in order to improve user experiences and information retrieval in social media.
Unclear, or in worst case misleading, tagging leads to information loss in social media. Especially, constructing storytelling or narration between pieces of user generated content becomes impossible without socially constructed tagging semantics. Furthermore, tagging can be seen as a one key element when building platforms for personalized and adaptive media services.
Probability to choose a tag is only about frequencies. The real challenges are related to explanative power of tags: if some tag is very frequent, its explanative power is low. Furthermore, when the tag is used rarely, it is not useful for searches. By using complex semantics between tags, we can improve the usability of the whole tagging system.
More information about technologies and philosophies behind the agents on Teachable Media Agents -blog.
