Quantifying the quality of a systems approach

Determining a systems design, analysis or approach to be of high or low quality remains a subjective assessment. Our field requires the ability to objectively grade the quality of a systems approach in advance of implementation and then correlate that assessment with outcomes. We issue a call-to-arms and present a strategy for quantitatively assessing the quality of systems thinking in an unread corpus of documents based on the previously published Dimensions of Systems Thinking. This strategy involves statistical semantic characterization through a process of supervised learning, term frequency and inverse document frequency (tf-idf), cosine similarity and Naïve Bayes classifiers, specifically Rocchio classifiers and quadratic discriminant classification. The results of our study demonstrate that our proposed capability can be achieved with a high degree of selectivity.