A Systematic Literature Review: Are Automated Essay Scoring Systems Competent in Real-Life Education Scenarios?

Artificial intelligence technology is becoming increasingly essential to education. The outbreak of COVID-19 in recent years has led many schools to launch online education. Automated online assessments have become a hot topic of interest, and an increasing number of researchers are studying Automated Essay Scoring (AES). This work seeks to summarise the characteristics of current AES systems used in English writing assessment, identify their strengths and weaknesses, and finally, analyse the limits of recent studies and research trends. Search strings were used to retrieve papers on AES systems from 2018 to 2023 from four databases, 104 of which were chosen to be potential to address the posed research aims after study selection and quality evaluation. It is concluded that the existing AES systems, although achieving good results in terms of accuracy in specific contexts, are unable to meet the needs of teachers and students in real teaching scenarios. The improvements of these systems relate to the scalability of the system for assessing different topics or styles of the essays, the accuracy of the model’s predicted scores, as well as the reliability of outcomes: improving the robustness of AES models with some adversarial inputs, the richness of AES system functionality, and the development of AES assist tools.