Widespread use of computer and Internet leads to an abundant supply of information, so that many services for facilitating fluent utilization of the information have appeared. However, many computer users are not so familiar with such services that they need assistant systems to use the services easily. In the case of Internet portal services, users' e-mail questions are answered by operator, but increasing number of users brings plenty of burdens. In this paper, we propose a two-level self-organizing map (SOM) that automatically responds to the users' questions on Internet, and helps them to find their answer for themselves by browsing the map hierarchically. The method consists of keyword clustering SOM that reduces a variable length question to a normalized vector, and document classification SOM that classifies the question into an answer class. The final map is also used for browsing. Experiments with real world data from Hanmail net, the biggest portal service in Korea, show the usefulness of the proposed method. Also, the browsing based on the map is conceptual and efficient.