Formative assessment and personalised feedback are commonly recognised as key factors both for improving students’ performance and increasing their motivation and engagement (Gibbs and Simpson, 2005). Currently, in large and massive open online courses (MOOCs), technological solutions to give feedback are often limited to quizzes of different kinds. At present, one of our challenges is to provide feedback for open-ended questions through semantic technologies in a sustainable way. To face such a challenge, our academic team decided to use a test based on latent semantic analysis (LSA) and chose an automatic assessment tool named G-Rubric. G-Rubric was developed by researchers at the Developmental and Educational Psychology Department of UNED (Spanish national distance education university). By using G-Rubric, automated formative and iterative feedback was provided to students for different types of open-ended questions (70–800 words). This feedback allowed students to improve their answers and writing skills, thus contributing both to a better grasp of concepts and to the building of knowledge. In this paper, we present the promising results of our first experiences with UNED business degree students along three academic courses (2014–15, 2015–16 and 2016–17). These experiences show to what extent assessment software such as G-Rubric is mature enough to be used with students. It offers them enriched and personalised feedback that proved entirely satisfactory. Furthermore, G-Rubric could help to deal with the problems related to manual grading, even though our final goal is not to replace tutors by semantic tools, but to give support to tutors who are grading assignments.

中文翻译：

---

在大型课程和MOOC中使用语义技术进行形成性评估和评分

形成性评估和个性化反馈通常被认为是提高学生表现，提高他们的动机和参与度的关键因素（Gibbs和Simpson，2005）。当前，在大规模的公开在线课程（MOOC）中，提供反馈的技术解决方案通常仅限于各种测验。当前，我们面临的挑战之一是通过语义技术以可持续的方式为开放式问题提供反馈。面对这样的挑战，我们的学术团队决定使用基于潜在语义分析（LSA）的测试，并选择了一个名为G-Rubric的自动评估工具。G-Rubric由UNED（西班牙国立远程教育大学）的发展与教育心理学系的研究人员开发。通过使用G-Rubric，针对不同类型的开放式问题（70-800字），向学生提供了自动形成和迭代反馈。这种反馈使学生能够改善他们的答案和写作技巧，从而有助于更好地理解概念和建立知识。在本文中，我们通过三个学术课程（2014-15、2015-16和2016-17）介绍了与UNED商业学位学生的初次体验所取得的令人鼓舞的结果。这些经验表明，诸如G-Rubric之类的评估软件已经成熟到可以与学生一起使用的程度。它为他们提供了丰富而个性化的反馈，证明是完全令人满意的。此外，即使我们的最终目标不是用语义工具代替导师，G-Rubric也可以帮助解决与手动评分有关的问题。