This paper addresses a new multimedia data mining framework for the extraction of events in videos by using decision tree logic. The aim of our DEVDT (Detection and Extraction of Videos using Decision Trees) system is for improving the indexing and retrieval of multimedia information. The extracted events can be used to index the videos. In this system we have considered C4.5 Decision tree algorithm 3 which is used for managing both continuous and discrete attributes. In this process, firstly we have adopted an advanced video event detection method to produce event boundaries and some important visual features. This rich multi-modal feature set is filtered by a pre-processing step to clean the noise as well as to reduce the irrelevant data. This will improve the performance of both Precision and Recall. After producing the cleaned data, it will be mined and classified by using a decision tree model. The learning and classification steps of this Decision tree are simple and fast. The Decision Tree has good accuracy. Subsequently, by using our system we will reach maximum Precision and Recall i.e. we will extract pure video events effectively and proficiently.