This paper proposed a new approach that integrated an artificial market simulation and text-mining. In this approach first economic trends were extracted from text data circulating in the real world. Then, the trends were inputted into the market simulation. The simulation could support users’ action to the actual market. This approach was used for the decision of exchange rate policy and suggested that the combination of interest rate and intervention operation was effective for the stabilization of the yen–dollar rate from 1994 to 1995. This approach can offer a useful social simulation as a tool to users.