No abstract

Automated essay scoring (AES) is a compelling topic in Learning Analytics for the primary reason that recent advances in AI find it as a good testbed to explore artificial supplementation of human creativity. However, a vast swath of research tackles AES only holistically; few have even developed AES models at the rubric level, the very first layer of explanation underlying the prediction of holistic scores. Consequently, the AES black box has remained impenetrable. Although several algorithms from Explainable Artificial Intelligence have recently been published, no research has yet investigated the role that these explanation models can play in: (a) discovering the decision-making process that drives AES, (b) fine-tuning predictive models to improve generalizability and interpretability, and (c) providing personalized, formative, and fine-grained feedback to students during the writing process. Building on previous studies where models were trained to predict both the holistic and rubric scores of essays, using the Automated Student Assessment Prize's essay datasets, this study focuses on predicting the quality of the writing style of Grade-7 essays and exposes the decision processes that lead to these predictions. In doing so, it evaluates the impact of deep learning (multilayer perceptron neural networks) on the performance of AES. It has been found that the effect of deep learning can be best viewed when assessing the trustworthiness of explanation models. As more hidden layers were added to the neural network, the descriptive accuracy increased by about 10%. This study shows that faster (up to three orders of magnitude) SHAP implementations are as accurate as the slower model-agnostic one. It leverages the state-of-the-art in natural language processing, applying feature selection on a pool of 1592 linguistic indices that measure aspects of text cohesion, lexical diversity, lexical sophistication, and syntactic sophistication and complexity. In addition to the list of most globally important features, this study reports (a) a list of features that are important for a specific essay (locally), (b) a range of values for each feature that contribute to higher or lower rubric scores, and (c) a model that allows to quantify the impact of the implementation of formative feedback.

No abstract

A smart learning environment is characterized by the key provision of personalized learning experiences. To approach different degrees of personalization in online learning, this article introduces a framework called Smart Competence Analytics in LEarning (SCALE) that tracks finer-level learning experiences and translates them into opportunities for customized feedback, reflection, and regulation. The SCALE framework is implemented in four layers: the sensing layer, the analysis layer, the competence layer, and the visualization layer. The sensing layer provides the datasets to support context-awareness through state-of-the-art sensing technologies. The analysis layer, by the means of powerful code analysis tools, derives performance metrics (e.g., learner coding metrics) which serve as input to the competence layer to identify proficiency levels of learners. Finally, a learning analytics dashboard called MI-DASH (visualization layer) allows interaction with performance and competence metrics. The current SCALE system has been used in a study to track the habits, performances, and competences of novice programmers. Growth of coding competences of first-year engineering students has been captured in a continuous manner. Students have been provided with customized feedback to optimize their learning paths. The article describes the analytics-based approach pursued in the study and highlights key findings.

No abstract