“…NLP methods are popular in computational social science (see also Nguyen, 2017; O’Connor et al, 2011), and they have yielded important insights on textual data in the field of education. For example, they have been used to analyze online and in-person class discussions (Fesler et al, 2019; Lugini et al, 2018), topics in dissertation abstracts (Munoz-Najar Galvez et al, 2019), and disciplinary differences in students’ academic writing (Crossley et al, 2017). A variety of NLP tools, such as Coh-Metrix (Graesser et al, 2014; McNamara et al, 2014), the Tool for the Automatic Analysis of Text Cohesion (TAACO; Crossley et al, 2016), and ReaderBench (Dascalu et al, 2014), have been used to characterize text cohesion, difficulty, and complexity in learning analytics and education data mining (Crossley & Kyle, 2018).…”