The analysis searches for electroweak diboson (WW/WZ/ZZ) production in association with a high-mass dijet system, using data from proton–proton collisions at a center-of-mass energy of √s = 13 TeV; the total dataset corresponds to an integrated luminosity of 139 fb−1. The analysis is performed in the semileptonic final states which include a hadronic decay boson and a leptonic decay one. The analysis is split into three channels according to the number of electrically charged leptons from the leptonic boson decay: 0-lepton, 1-lepton, and 2-lepton channels. The focus of this thesis is an approach to enhance the separation between the VBS signal and the backgrounds in the 1-lepton channel using artificial neural network models. This approach is developed using Monte Carlo simulated events in the semi-leptonic VBS analysis and tested using ATLAS data for improving the sensitivity of the analysis to the target signal. The semileptonic vector boson scattering production of WW/WZ in the 1-lepton channel is measured with an observed (expected) significance of 5.78σ (5.98σ) standard deviations.