No abstract

This article describes several approaches to assessing student understanding using written explanations that students generate as part of a multiple-document inquiry activity on a scientific topic (global warming). The current work attempts to capture the causal structure of student explanations as a way to detect the quality of the students' mental models and understanding of the topic by combining approaches from Cognitive Science and Artificial Intelligence, and applying them to Education. First, several attributes of the explanations are explored by hand-coding and leveraging existing technologies (LSA and Coh-Metrix). Then, we describe an approach for inferring the quality of the explanations using a novel, two-phase machine learning approach for detecting causal relations and the causal chains that are present within student essays. The results demonstrate the benefits of using a machine learning approach for detecting content, but also highlight the promise of hybrid methods that combine ML, LSA and Coh-Metrix approaches for detecting student understanding. Opportunities to use automated approaches as part of Intelligent Tutoring Systems that provide feedback toward improving student explanations and understanding are discussed.

The present study explored different approaches for automatically scoring student essays that were written on the basis of multiple texts. Specifically, these approaches were developed to classify whether or not important elements of the texts were present in the essays. The first was a simple pattern-matching approach called "multi-word" that allowed for flexible matching of words and phrases in the sentences. The second technique was latent semantic analysis (LSA), which was used to compare student sentences to original source sentences using its high-dimensional vectorbased representation. Finally, the third was a machinelearning technique, support vector machines, which learned a classification scheme from the corpus. The results of the study suggested that the LSA-based system was superior for detecting the presence of explicit content from the texts, but the multi-word pattern-matching approach was better for detecting inferences outside or across texts. These results suggest that the best approach for analyzing essays of this nature should draw upon multiple natural language processing approaches.

Abstract. In the US in particular, there is an increasing emphasis on the importance of science in education. To better understand a scientific topic, students need to compile information from multiple sources and determine the principal causal factors involved. We describe an approach for automatically inferring the quality and completeness of causal reasoning in essays on two separate scientific topics using a novel, twophase machine learning approach for detecting causal relations. For each core essay concept, we initially trained a window-based tagging model to predict which individual words belonged to that concept. Using the predictions from this first set of models, we then trained a second stacked model on all the predicted word tags present in a sentence to predict inferences between essay concepts. The results indicate we could use such a system to provide explicit feedback to students to improve reasoning and essay writing skills.

No abstract