Search

Background: Formative assessments are needed to enable monitoring how student knowledge develops throughout a unit. Constructed response items which require learners to formulate their own free‐text responses are well suited for testing their active knowledge. However, assessing such constructed responses in an automated fashion is a complex task and requires the application of natural language processing methodology. In this article, we implement and evaluate multiple machine learning models for coding energy knowledge in free‐text responses of German K‐12 students to items in formative science assessments which were conducted during synchronous online learning sessions. Dataset: The dataset we collected for this purpose consists of German constructed responses from 38 different items dealing with aspects of energy such as manifestation and transformation. The units and items were implemented with the help of project‐based pedagogy and evidence‐centered design, and the responses were coded for seven core ideas concerning the manifestation and transformation of energy. The data was collected from students in seventh, eighth and ninth grade. Methodology: We train various transformer‐ and feature‐based models and compare their ability to recognize the respective ideas in students' writing. Moreover, as domain knowledge and its development can be formally modeled through knowledge networks, we evaluate how well the detection of the ideas within responses translated into accurate co‐occurrence‐based knowledge networks. Finally, in terms of the descriptive accuracy of our models, we inspect what features played a role for which prediction outcome and if the models pick up on undesired shortcuts. In addition to this, we analyze how much the models match human coders in what evidence within responses they consider important for their coding decisions. Results: A model based on a modified GBERT‐large can achieve the overall most promising results, although descriptive accuracy varies much more than predictive accuracy for the different ideas assessed. For reasons of comparability, we also evaluate the same machine learning architecture using the SciEntsBank 3‐Way benchmark with an English RoBERTa‐large model, where it achieves state‐of‐the‐art results in two out of three evaluation categories. Lay Description: What is already known about this topic?: Formative assessments are needed to test and monitor the development of learners' knowledge throughout a unit to provide them with appropriate automated feedback.Constructed response items which require learners to formulate their own free‐text responses are well suited for testing their active knowledge.Assessing constructed responses in an automated fashion is a widely researched topic, but the problem is far from solved and most of the work focuses on predicting holistic scores or grades.To allow for a more fine‐grained and analytic assessment of learners' knowledge, systems which go beyond predicting simple grades are required.To guarantee that models are stable and make their predictions for the correct reasons, methods for explaining the models are required. What this papers adds?: A core topic in physics education is the concept of energy.We implement and evaluate multiple systems based on natural language processing technology for assessing learners' conceptual knowledge about energy physics using transformer language models as well as feature‐based approaches.The systems assess students' knowledge about various forms of energy, indicators for the same and the transformation of energy from form into another.As our systems are based on machine learning methodology, we introduce a novel German short answer dataset for training them to detect the respective knowledge elements within students' free‐text responses.We evaluate the performance of these systems using this dataset as well as the well‐established SciEntsBand‐3‐Way dataset and manage to achieve, to our best knowledge, new state‐of‐the‐art results for the latter.Moreover, we apply methodology for explaining model predictions to assess whether predictions are carried out for the correct reasons. Implications for practice and/or policy: It is indeed possible to assess constructed responses for the demonstrated knowledge about energy physics in an analytic fashion using natural language processing.Transformer language models can outperform more specialized feature‐based approaches for this task in terms of predictive and descriptive accuracy.Co‐occurrences of different concepts within the same responses can lead models to learn undesired shortcuts which make them unstable. [ABSTRACT FROM AUTHOR]

Background: Assignments that involve writing based on several texts are challenging to many learners. Formative feedback supporting learners in these tasks should be informed by the characteristics of evolving written product and by the characteristics of learning processes learners enacted while developing the product. However, formative feedback in writing tasks based on multiple texts has almost exclusively focused on essay product and rarely included SRL processes. Objectives: We explored the viability of using product and process features to develop machine learning classifiers that identify low‐ and high‐performing essays in a multi‐text writing task. Methods: We examined learning processes and essay submissions of 163 graduate students working on an authentic multi‐text writing assignment. We utilised learners' trace data to obtain process features and state‐of‐the‐art natural language processing methods to obtain product features for our classifiers. Results and Conclusions: Of four popular classifiers examined in this study, Random Forest achieved the best performance (accuracy = 0.80 and recall = 0.77). The analysis of important features identified in the Random Forest classification model revealed one product (coverage of reading topics) and three process (elaboration/organisation, re‐reading and planning) features as important predictors of writing quality. Major Takeaways: The classifier can be used as a part of a future automated writing evaluation system that will support at scale formative assessment in writing tasks based on multiple texts in different courses. Based on important predictors of essay performance, a guidance can be tailored to learners at the outset of a multi‐text writing task to help them do well in the task. Lay Description: What is already known about this topic?: Both product and process features should be used to inform formative feedback on writing.Providing product‐ and process‐oriented feedback to learners is challenging.Automatic writing evaluation systems have mainly relied upon product features.Automated analysis of learners' trace data and their essay drafts is a promising venue. What this paper adds?: An accurate machine learning classifier that identifies low‐ and high‐scoring essays.The classifier utilized both product and process features.We obtained process features from learners' trace data in digital learning environment.We computed product features using state‐of‐the‐art text analytical methods. Implications for practice and/or policy: The classifier can be used as a part of a future automated writing evaluation system.We revealed learning processes and essay characteristics that influence performance.Based on important predictors of performance, formative feedback can be given to learners. [ABSTRACT FROM AUTHOR]

Background: Teachers often rely on the use of open‐ended questions to assess students' conceptual understanding of assigned content. Particularly in the context of mathematics; teachers use these types of questions to gain insight into the processes and strategies adopted by students in solving mathematical problems beyond what is possible through more close‐ended problem types. While these types of problems are valuable to teachers, the variation in student responses to these questions makes it difficult, and time‐consuming, to evaluate and provide directed feedback. It is a well‐studied concept that feedback, both in terms of a numeric score but more importantly in the form of teacher‐authored comments, can help guide students as to how to improve, leading to increased learning. It is for this reason that teachers need better support not only for assessing students' work but also in providing meaningful and directed feedback to students. Objectives: In this paper, we seek to develop, evaluate, and examine machine learning models that support automated open response assessment and feedback. Methods: We build upon the prior research in the automatic assessment of student responses to open‐ended problems and introduce a novel approach that leverages student log data combined with machine learning and natural language processing methods. Utilizing sentence‐level semantic representations of student responses to open‐ended questions, we propose a collaborative filtering‐based approach to both predict student scores as well as recommend appropriate feedback messages for teachers to send to their students. Results and Conclusion: We find that our method outperforms previously published benchmarks across three different metrics for the task of predicting student performance. Through an error analysis, we identify several areas where future works may be able to improve upon our approach. Lay Description: What is already known about this topic: Open‐ended questions are used by teachers in the domain of mathematics to assess their students understanding but automated support for these types of questions are limited in online learning platforms. Recent advancements in areas of machine learning and natural language processing have led to promising results in a range of domains and applications. What this paper adds: Emulating how teachers identify similar student answers can be used to build tools that support teachers in assessing and providing feedback to student open‐ended work. Implications for practice: Developing better automated supports can increase the amount of direct feedback students receive to guide their learning. [ABSTRACT FROM AUTHOR]

Background: In the context of large‐scale educational assessments, the effort required to code open‐ended text responses is considerably more expensive and time‐consuming than the evaluation of multiple‐choice responses because it requires trained personnel and long manual coding sessions. Aim: Our semi‐supervised coding method eco (exploring coding assistant) dynamically supports human raters by automatically coding a subset of the responses. Method: We map normalized response texts into a semantic space and cluster response vectors based on their semantic similarity. Assuming that similar codes represent semantically similar responses, we propagate codes to responses in optimally homogeneous clusters. Cluster homogeneity is assessed by strategically querying informative responses and presenting them to a human rater. Following each manual coding, the method estimates the code distribution respecting a certainty interval and assumes a homogeneous distribution if certainty exceeds a predefined threshold. If a cluster is determined to certainly comprise homogeneous responses, all remaining responses are coded accordingly automatically. We evaluated the method in a simulation using different data sets. Results: With an average miscoding of about 3%, the method reduced the manual coding effort by an average of about 52%. Conclusion: Combining the advantages of automatic and manual coding produces considerable coding accuracy and reduces the required manual effort. Lay Description: We present a new (semi‐)automatic method for coding text responses.The method supports the human coders in their work and acts as an assistant. The exploring coding assistant eco groups all responses in a first unsupervised step and explore the clusters by continuously selecting responses for manual coding to gather supervised information.Based on the coding information, eco automatically codes similar responses and reduces the manual coding effort. [ABSTRACT FROM AUTHOR]