A Text Analytics Framework for Supplier Capability Scoring Supported by Normalized Google Distance and Semantic Similarity Measurement Methods

Abstract

The unstructured data available on the websites of manufacturing suppliers and contractors can provide valuable insights into their technological and organizational capabilities. However, since the capability data are often represented in an unstructured and informal fashion using natural language text, it is not easy to efficiently search and analyze the capability data and learn from it. The objective of this work is to propose framework to enable automated classification and ranking of suppliers based on their online capability descriptions in the context of a supplier search and discovery use case. The proposed text analytics methods used in this work are supported by a formal thesaurus that uses SKOS (Simple Knowledge Organization System) that provides lexical and structural semantics. Normalized Google Distance (NGD) is used as the metric for measuring the relatedness of terms when ranking suppliers based on their similarities with the queried capabilities. The proposed framework is validated experimentally using a hypothetical supplier search scenario. The results indicate that the generated ranked list is highly correlated with human judgment, especially when the search space is partitioned into multiple classes of suppliers with distinct capabilities. However, the correlation decreases when multiple overlapping classes of suppliers are merged together to form a heterogenous search space. The proposed framework can support supplier screening and discovery solutions by improving the precision, reliability, and intelligence of their underlying search engines.