Using automated feedback to develop writing proficiency

AI in the Foreign Language Classroom: A Pedagogical Overview of Automated Writing Assistance Tools

“…These studies have also shown that among the many types of revisions made by students using AWE systems, lexical appropriateness and grammar accuracy were the most frequent as opposed to revisions for content or structure [14,16]. Furthermore, although significant improvement may be seen in individual texts due to the use of AWE systems, these studies hardly ever showed any long-term improvement or even were able to prove that learning did take place [29]. Some researchers, such as Ranalli [30], went further and strongly criticized the use of AWE tools in the language classroom and pointed out that these tools "did not live up to expectations" (p. 2).…”

“…Burstein et al [14]; Ortega [15]; Bridgeman and Ramineni [16]; Ranalli et al [17]; Godwin-Jones [18]; Hibert [19] Hussein et al [20]; Warschauer et al [21]; Saricaoglu [22]; Link et al [23]; Peng et al [24]; Palermo and Wilson [25] Nunes et al [26]; Camacho et al [27]; Godwin-Jones [28]; Huang and Wilson [29]; Ranalli [30] Automated writing corrective feedback (AWCF) tools (text editors supplying synchronous feedback)…”

“…Jiang et al [68]; John and Woll [40]; Koltovskaia [2]; Woodworth and Barkaoui [69]; Hellmich and Vinall [7] Hellmich and Vinall [7]; Kessler [70]; Ling et al [71]; Ranalli [30]; Li [72] Li [72]; Knowles [73]; Pellet and Myers [9]; Sumakul et al [74]; Fyfe [75] Adopting ecological perspectives Larsen-Freeman [76]; Zhang and Hyland [77]; Hockly [78]; Patout and Cordy [79]; Jiang et al [68]; Koltovskaia [2]; Link et al [23] Lee [52]; Woodworth and Barkaoui [69]; Zhang [80]; Hellmich and Vinall [7]; Nunes et al [26]; Ranalli [30] Huang and Wilson [29]; Li [72]; Lieshout and Cardoso [81]; Pellet and Myers [9]; Sun and Fan [82] practice is provided to students. Variables related to students when discussing the effectiveness of using AWE are also important and maybe more telling.…”

“…Several studies have shown that the earlier the stage during which AWE is provided, the more useful AWE feedback will be [17,29]. These studies have also shown that among the many types of revisions made by students using AWE systems, lexical appropriateness and grammar accuracy were the most frequent as opposed to revisions for content or structure [14,16].…”

“…Organization, coherence, and argumentation strength are all examples of areas that AWE systems may not be of great help. This may be attributed to the complexity of human language that makes it very difficult for AI systems to fully understand the richness and complexity of human language and its contextual pragmatic and contextual aspects of a language [29,86].…”