This assumption is backed by research that indicates self-disclosure is easier by using a computer (Richman et al.
], but as of now, there is yet not a widely agreed definition of reflection.
Despite the importance of reflection for education, there is little research on artificial intelligence techniques to automate the analysis of writings regarding reflective thinking.
Currently, the common educational practice to analyze and assess reflective writings is a manual process.
Furthermore, there has been some research using dictionary and rule-based approaches (see the following review section), but in general, not much is known about the extent to which automated methods can be used to reliably analyze texts regarding categories of reflective writing models.
This research replicates the aspect of the manual content analysis that assigns labels to text segments with automated means.This study evaluates whether machine learning can be used to automate this manual analysis.The study investigates eight categories that are often used in models to assess reflective writing, and the evaluation is based on 76 student essays (5080 sentences) that are largely from third- and second-year health, business, and engineering students.These writings are different as they are centered on the personal thought process and how to learn from individual experiences.The writings are often very personal and can contain references to feelings. They may consider the perspectives of people who are important in their context or draw conclusions from contexts that are valued by the author.The labeled text units are used to calculate scores that indicate the quality of reflection found in the writing (for example, see Clarkeburn and Kettula ).This analysis is currently manual, as there is a lack of knowledge about automated methods specific to reflective writing.This research further investigates the potential of supervised machine learning algorithms to reliably annotate text segments of writings according to categories of a reflective writing model.Researching automated methods to analyze reflection is important because the manual analysis poses constraints to teaching and research and may hamper deeply personal reflections.Very often, they are analyzed by following the principles of the content analysis method (Krippendorff ).The typical content coding task of reflective writings entails the manual labeling of text units according to categories of a reflective writing model.