THE MEASUREMENT OF TEXTUAL COHERENCE WITH LATENT SEMANTIC ANALYSIS

Latent Semantic Analysis (LSA) is used as a technique for measuring th e coherence of texts. By comparing the vectors for 2 adjoining segment s of text in a high-dimensional semantic space, the method provides a characterization of the degree of semantic relatedness between the seg ments. We illustrate the approach for predicting coherence through rea nalyzing sets of texts from 2 studies that manipulated the coherence o f texts and assessed readers' comprehension. The results indicate that the method is able to predict the effect of text coherence on compreh ension and is more effective than simple term-term overlap measures. I n this manner, LSA can be applied as an automated method that produces coherence predictions similar to propositional modeling. We describe additional studies investigating the application of LSA to analyzing d iscourse structure and examine the potential of LSA as a psychological model of coherence effects in text comprehension.