In this era of deep learning where AI and machine learning models are used in well-known applications such as speech to text, real-time translation, image recognition, requires a large amount of data for the training. To process a large amount the data, model efficiency is a major concern, for this, there are few optimizations' methods being developed by a different researcher. In our research, we briefly discussed the famous optimization method such as PSO and their implementation with different machine learning models and perform experiments with different volumes of textual data and overview the performance with or without PSO algorithm, besides we also utilize a similar approach with neural networks. Experimental results show the proposed overview significance on data volume.