Driver's behavior is expressed by the intentional and unintentional actions the driver performs while driving a motor vehicle. This behavior could be influenced by several factors such as fatigue, drowsiness, vehicle surroundings, and distraction state. Driver's behavior could be normal, risky or aggressive. Risky and aggressive behaviors, such as harsh braking and rapid acceleration can lead to traffic accidents. Monitoring, analyzing and improving driver's behavior can reduce traffic collisions and enhance road safety. Different approaches have been followed for the detection and identification of driver's behavior. Rule-based Machine learning (ML) and deep learning (DL) approaches have succeeded to mine dynamical characteristics of time series. However, they have some challenges that make them unsuitable for many classification tasks including the selection of efficient architectures and corresponding hyper-parameters, as well as slow training and limited labeled data. Fusion and attention mechanisms through hybrid approaches were found to be more suitable for time series sensor data analysis. Transfer learning addresses useful approaches for making use of learning applied to other applications. Maneuver detection represents a serious characteristic of driver's behavior identification. A recent approach for extracting maneuvers from high-frequency telematics data is through time series motifs detection algorithms. Motifs extraction is preferred over ML and DL approaches as it does not not requie labels, which is extremely time-consuming to collect. This work focuses on the latest techniques for classifying driver's behavior in time series data, and summarizes the pros and cons of the different categories.