Companion Modeling is a methodology used to facilitate adaptive management of renewable resources by their users. It is using role-playing games (RPG) and multiagent simulations to validate initial models representing the functioning of complex systems to be managed. In this research, we propose a novel agent model construction methodology in which classification learning is applied to the RPG log data in Companion Modeling. This methodology enables a systematic model construction that handles multi-parameters, independent of the modelers ability. There are three problems in applying classification learning to the RPG log data: 1) It is difficult to gather enough data for the number of features because the cost of gathering data is high. 2) Noise data can affect the learning results because the amount of data may be insufficient. 3) The learning results should be explained as a human decision making model and should be recognized by the expert as reflecting reality. We realized an agent model construction system using the following two approaches: 1) Using a future selection method, the feature subset that has the best prediction accuracy is identified. In this process, the important features chosen by the expert are always included. 2) The expert eliminates irrelevant features from the learning results after evaluating the learning model through a visualization of the results. Finally, using the RPG log data from a Companion Modeling case study on rice production in northeastern Thailand, we confirm the capability of this methodology.