Can sentence structure and complexity be used to identify authors in dialogues between students and tutors? Are there relationships between how an individual structures their sentences and their learning curve?;This thesis uses machine learning techniques and statistical analysis in two separate educational experiments. In the first experiment we attempt to find relationships between students' written essay responses to physics questions and their learning of the physics data. To find these relationships, we used multiple types of sentence data such as noun phrases, verb phrases, and other aspects of student writings.;In the second experiment we attempt to find the same relationships as in the above physics experiment, but also attempt to do author identification and to find the relationships (if any) between the teachers' linguistics and effectiveness.;Along with the aspects used in the physics experiment, we also used additional aspects like the Flesch Reading Ease test, and the percentage of domain words. The processes we used to find these features include the C4.5 decision tree algorithm (WEKA's implementation J48), the cluster algorithm KMeans (WEKA's implementation SimpleKMeans), and a statistical method, Student's t.
展开▼
