This paper provides initial analysis in identifying possible Web services composition using context-based semantic matching. Context-based semantic matching allows service composition to be expanded beyond simple term matching and reduces erroneous compositions. A common method of context extraction is used to compare two types of service description, textual and WSDL. The approach is unique since it provides the Web service designer with an explicit numeric estimation of the extent to which a composition "makes sense." Motivation for the work is displayed with examples from Web services in the field of business. Categories and Subject Descriptors H.3.5 [Online Information Services]: Web-based services; H.3.1 [Information Storage And Retrieval]: Content Analysis and Indexing; I.2.4 [Knowledge Representation Formalisms and Methods]: Semantic networks General Terms Algorithms, Design, Measurement Keywords Web services, Context, Semantics