No abstract

This paper focuses on the problem of assigning relative priorities to requirements specified in the natural language. Proposed method includes processing plain text requirements specifications in order to extract multidimensional statistical features from the given requirement text to estimate latent semantic cohesion among the requirements as well as specific information contained within requirements. Using these estimates, latent semantic centrality and relative information specificity scores are derived for each requirement, which form the basis for assigning relative priorities to the requirements. We next extend this approach to clusters of requirements, where in requirements are clustered into semantically coherent groups and relative priorities are assigned to these groups of requirements. We further discuss a method for identifying semantically isolated requirements which might demand further analysis and elaboration by user. Suggested approach is specifically amenable to automated tool support as the case of prototype tool used in experiments to assess feasibility and effectiveness of the proposed approach demonstrates.

No abstract