Jeffrey Wong and Jason Hong

ACM Conference on Human Factors in Computing Systems (CHI)

Work in Progress

A tremendous amount of semi-structured data is available today on the web but is not necessarily in a form which is suitable for a user's tasks. For example, a website may show a listing of local events but a user wants to filter out those which are too far from him. To address this problem, we are developing a tool called Marmite that helps users extract data from web pages and create new applications using a dataflow architecture in a manner similar to Unix pipes. In this paper, we describe formative user studies, some evaluations of low-fidelity prototypes, and a set of design recommendations for this tool.