Simon Hughes, Peter Hastings, Joseph Magliano, Susan Goldman, Kimberly Lawless
Integrating information across multiple sources is an important literacy skill, yet there has been little research into automated methods for measuring integration in written text. This study investigated the efficacy of three different algorithms at classifying student essays according to an expert model of the essay topic which categorized statements by argument function, including claims and integration. A novel classification algorithm is presented which uses multi-word regular expressions. Its performance is compared to that of Latent Semantic Analysis and several variants of the Support Vector Machine algorithm at the same classification task. One variant of the SVM approach worked best overall, but another proved more successful at detecting integration within and across texts. This research has important implications for systems that can gauge the level of integration in written essays.
The final publication is available at Springer via https://doi.org/10.1007/978-3-642-30950-2_35.