Context-aware applications in the real world adapt their behavior to contexts abstracted from real-world situations sensed as physical quantities by heterogeneous and distributed sensors. Most of the adaptations are programmed as rules derived from human experience in making environments comfortable and efficient. Preparing sufficient rules, however, is difficult because oversights and exceptional contexts are inevitable. In this paper, we focus on sensor data fluctuations and calculate probabilities that indicate the frequency of such sensor data fluctuations. The results help us find previously unnoticed situations that the context-aware applications should cope with. We applied this method to log data captured in our office in order to evaluate the methods? capabilities and then considered the feasibility of abstracting these situations into rules.