The measurement of textual coherence with latent semantic analysis

TLDR

Latent Semantic Analysis measures textual coherence by comparing high‑dimensional semantic vectors of adjacent text segments. The study aims to demonstrate that LSA can predict how text coherence affects reader comprehension and to explore its use for analyzing discourse structure and modeling coherence effects. The authors reanalyze two experimental corpora that manipulated coherence and assessed comprehension, and conduct additional studies applying LSA to discourse analysis. Results show LSA predicts coherence‑comprehension effects better than simple term overlap and yields automated coherence predictions comparable to propositional models.

Abstract

Latent Semantic Analysis (LSA) is used as a technique for measuring the coherence of texts. By comparing the vectors for 2 adjoining segments of text in a high‐dimensional semantic space, the method provides a characterization of the degree of semantic relatedness between the segments. We illustrate the approach for predicting coherence through reanalyzing sets of texts from 2 studies that manipulated the coherence of texts and assessed readers’ comprehension. The results indicate that the method is able to predict the effect of text coherence on comprehension and is more effective than simple term‐term overlap measures. In 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 discourse structure and examine the potential of LSA as a psychological model of coherence effects in text comprehension.