Abstract Estilector is a free online system for the automatic proofreading of academic writing in Spanish. It works by indicating possible errors in the text and, in some cases, suggesting their correction. Not always the issues that the program finds are necessarily incorrect from the normative point of view, but they are aspects that could be improved from the point of view of the requirements of an academic text, especially the textual and discursive aspects. Along these lines, the software is designed primarily for the detection of textual problems, although it also incorporates, to a lesser extent, some lexical, grammatical, and spelling corrections. In addition to offering corrections, it supports the learning of writing skills by providing formative feedback, so it falls into the category of a writing support tool of the automated writing evaluation type or AWE (Strobl et al., 2019). In that line, it provides bibliographic references to facilitate the learning of the aspects considered improvable and explanations which exceed the traditional concept of correction of word processors (cf. Dale & Viethen, 2021), such as Microsoft Word or Google Docs. In its years of existence, it has had a large number and variety of users and has been adapting to an audience that requires basic, cross-cutting support when writing. In this article, we offer a description of the current status of the project with its methods of error detection and revision as well as some final thoughts, including its limitations and some possibilities for future development, such as the following: 1) Adapting the software as a tool for writing assessment. It is necessary to incorporate modules that allow the program to be used as a support for the formal assessment of writing tasks in universities, in order to make the program more effective as a tool to support the learning of writing (Conijn et al., 2020). This implies at least considering the discursive genre variable, providing the teacher and the student with a quantitative and qualitative summary of the latter's performance, or the teacher being able to add comments to the feedback that the program provides automatically. 2) Incorporating different types of users. In line with the above, Estilector is projected as a tool that assumes that writing is, to a greater or lesser extent, a collective activity, in which the writer consults, submits for reading, and is evaluated by others (Hayes, 2012). For this reason, we plan that the program will be accessed by a user who can be assigned various roles, e.g., tutor or student. 3) Improving precision of the existing rules and incorporating new ones for the detection of different types of errors. The results of the evaluation presented in the paper offer insight into what aspect should be improved, which will be added to the lines of research already open.
Resumen Se describe Estilector, un sistema de retroalimentación automática de escritura académica en castellano. El software está orientado principalmente a la detección de problemas textuales, aunque también incorpora, en menor medida, correcciones gramaticales y ortográficas. Pretende apoyar el aprendizaje de la escritura aportando feedback formativo, y proporciona referencias bibliográficas y sugerencias de revisión más extensas que las de los procesadores de texto. El programa funciona actualmente en línea y es de acceso gratuito. En sus años de existencia, ha tenido gran número y variedad de usuarios, y se ha ido adaptando a un público que requiere apoyo básico y transversal a la hora de escribir. En este artículo ofrecemos una descripción del estado actual del proyecto con sus métodos de detección y revisión de errores además de algunas reflexiones finales, incluyendo sus limitaciones y posibilidades de desarrollo futuro.