Due to the personalized and diversified expression habits, the evaluation information in multiple criteria decision-making (MCDM) problems, especially those with multiple experts, may appear in heterogeneous forms. Converting heterogeneous expressions to a single representation would lead to information loss. To solve this challenge, this article aims to address the MCDM problems with heterogeneous linguistic expressions by unifying the operations of heterogeneous linguistic representations. To do so, we propose to use expectation values and entropy measures to describe the meaning of linguistic evaluation information. The expectation functions of ten kinds of linguistic representations are respectively defined based on the semantics of linguistic terms. The entropy measures of these representations are developed to reflect the inherent uncertainty of evaluations. Afterward, a computation model for heterogeneous linguistic representations is presented based on their expectation values and entropy. On this basis, an MCDM framework with personalized heterogeneous linguistic information is constructed. A numerical example about selecting the best green logistics for a business-to-customer e-commerce enterprise shows the advantages of the proposed method in modeling personalized linguistic evaluations and retaining uncertain information in the computation process.