Computational methods for analysis of language in graduate and undergraduate student texts

Abstract

Often, academic programs require students to write a thesis or research proposal. The review of such texts is a heavy load, especially at initial stages. Natural Language Processing techniques are employed to mine existing corpora of research proposals and theses to further assess drafts of college students in information technologies and computer science. In this chapter, we focus on examining specific sections of student writings, first seeking for the connection of ideas identifying the pattern of entities. Subsequently, we analyze the justification and conclusions sections, studying features such as the presence of importance in justification and the level of speculative words in a conclusion section. Experiments and results for the different analyses are explained in detail. Each analysis is independent and could allow the student to analyze their text with a set of tools with the aim of improving their writing.