World Wide Web can be seen as a massive memory for human activities and experiences. Not only do online news papers report on various events the public would be interested in but also personal and social media such as blog posts and twits reflect various personal activities experiences that may be related to other events or other activities. In this talk, I will introduce our ongoing efforts to capture activity-based human experiences from personal and social media by means of natural language processing techniques. Aggregated from individual sources with the aid of huge activity ontology constructed automatically, mined experiences can be utilized for “decision-on-the-go”, a primary capability to be realized with mobile applications.