This paper presents a novel deep learning-based (DL) approach to characterize short-fiber orientation in material extrusion large format additive manufacturing (LFAM). The method focuses on Acrylonitrile Butadiene Styrene (ABS) reinforced with short glass fibers 20%, a material widely used due to its enhanced mechanical performance. Traditional fiber orientation analysis, which relies on microscopy and manual image processing, is often costly and time-consuming. To address this, we developed Python algorithms to generate synthetic SEM-like images to train a Convolutional Neural Network (CNN). The proposed CNN accurately predicts the fiber orientation tensors directly from micrographs, with consistent results with conventional methods. The combination of synthetic data generation and deep learning provides a scalable and rapid alternative for fiber orientation analysis. This approach improves the analysis of fiber orientation in discontinuous composite materials and has the potential to be applied to additive manufacturing and other forming processes. This study demonstrates that combining deep learning with synthetic data generation provides an effective, scalable solution for fiber orientation analysis in LFAM, confirming that CNN-based methods can greatly improve material characterization. More accurate performance prediction and quality control could be achieved in fiber-reinforced additive manufacturing.