The wide adaptation of mobile devices embedded with mod- ern positioning technology enables the collection of valuable mobility data from users. At the same time, the large-scale user-generated data from social media, such as geo-tagged tweets, provide rich semantic information about events and locations. The combination of the mobility data and social media data brings opportunities for us to study the seman- tics behind people's movement, i.e., understand why a per- son travels to a location at a particular time. Previous work have used map or POI (point of interest) database as source for semantics. However, those semantics are static, and thus missing important dynamic event information. To provide dynamic semantic annotation, we propose to use contextual social media. More specifically, the semantics could be land- mark information (e.g., a museum or an arena) or event in- formation (e.g., sports games or concerts). The annotation method annotates words to each mobility records based on local density of words, estimated by Kernel Density Esti- mation model. The annotated mobility data contain rich and interpretable information, therefore can bene t appli- cations, such as personalized recommendation, targeted ad- vertisement, and movement prediction. Our system is built upon large-scale tweet datasets. A user-friendly interface is designed to support interactive exploration of the result.