Augmenting User Models with Real World Experiences to Enhance Personalization and Adaptation

Social media are media for social interaction that allow creating and exchanging user-generated content. The massive social content can provide rich resources for deriving social profiles that can augment user models and improve adaptation in traditional applications. However, potentially valuable social contributions can be buried within highly noisy content that is irrelevant or spam. This paper sketches a research roadmap toward augmenting user models with key user characteristics derived from social content. It then focuses on the first step: identifying and filtering noisy content to create data corpus about a specific activity. A novel, semantically enriched machine learning approach to filter the noisy content from social media is described. This is applied to a specific social source and activity: public comments on YouTube job interview videos. A potential application of the approach to augment user models in simulated experiential learning environments is discussed.