Themed collocated events, such as conferences, workshops, and seminars, invite people with related life experiences to connect with each other. In this era when people record lives through the Internet, individual experiences exist in different forms of digital contents. People share digital life records during collocated events, such as sharing blogs they wrote, Twitter posts they forwarded, and books they have read. However, connecting experiences during collocated events are challenging. Not only one is blind to the large contents of others, identifying related experiential items depends on how well experiences are retrieved. The collection of personal contents from all participants forms a valuable group repository, from which connections between experiences can be mined. Visualizing same or related experiences inspire conversations and support social exchange. Common topics in group content also help participants generate new perspectives about the collocated group. Advances in machine learning and data visualization provide automated approaches to process large data and enable interactions with data repositories. This position paper promotes the idea of event mining: how to utilize state-of-the-art data processing and visualization techniques to design event mining systems for connecting experiences during collocated activities. We discuss empirical and constructive problems in this design space, and our preliminary study of deploying a tabletop-based system, BlogCloud, which supports experience re-visitation and exchange with machine-learning and data visualization.