We propose and experimentally assess Semantic Word Error Rate (SWER), an innovative similarity measure for sentence plagiarism detection. SWER introduces a complex approach based on latent semantic analysis, which is capable of outperforming the accuracy of competitor methods in plagiarism detection. We provide principles and functionalities of SWER, and we complement our analytical contribution by means of a significant preliminary experimental analysis. Derived results are promising, and confirm to use the goodness of our proposal.
