An investigation into the extraction of useful information from the free text element of questionnaires, using a semi-automated summarisation extraction technique to generate text summarisation classifiers, is described. A realisation of the proposed technique, SARSET (Semi-Automated Rule Summarisation Extraction Tool), is presented and evaluated using real questionnaire data. The results of this approach are compared against the results obtained using two alternative techniques to build text summarisation classifiers. The first of these uses standard rule-based classifier generators, and the second is founded on the concept of building classifiers using secondary data. The results demonstrate that the proposed semi-automated approach outperforms the other two approaches considered.