An official website of the United States government
Involving students in scientific modeling practice is one of the most effective approaches to achieving the next generation science education learning goals. Given the complexity and multirepresentational features of scientific models, scoring student-developed models is time- and cost-intensive, remaining one of the most challenging assessment practices for science education. More importantly, teachers who rely on timely feedback to plan and adjust instruction are reluctant to use modeling tasks because they could not provide timely feedback to learners. This study utilized machine learn- ing (ML), the most advanced artificial intelligence (AI), to develop an approach to automatically score student- drawn models and their written descriptions of those models. We developed six modeling assessment tasks for middle school students that integrate disciplinary core ideas and crosscutting concepts with the modeling practice. For each task, we asked students to draw a model and write a description of that model, which gave students with diverse backgrounds an opportunity to represent their understanding in multiple ways. We then collected student responses to the six tasks and had human experts score a subset of those responses. We used the human-scored student responses to develop ML algorithmic models (AMs) and to train the computer. Validation using new data suggests that the machine-assigned scores achieved robust agreements with human consent scores. Qualitative analysis of student-drawn models further revealed five characteristics that might impact machine scoring accuracy: Alternative expression, confusing label, inconsistent size, inconsistent position, and redundant information. We argue that these five characteristics should be considered when developing machine-scorable modeling tasks.
more »
« less
Examining the Effect of Assessment Construct Characteristics on Machine Learning Scoring of Scientific Argumentation
Abstract Argumentation, a key scientific practice presented in theFramework for K-12 Science Education, requires students to construct and critique arguments, but timely evaluation of arguments in large-scale classrooms is challenging. Recent work has shown the potential of automated scoring systems for open response assessments, leveraging machine learning (ML) and artificial intelligence (AI) to aid the scoring of written arguments in complex assessments. Moreover, research has amplified that the features (i.e., complexity, diversity, and structure) of assessment construct are critical to ML scoring accuracy, yet how the assessment construct may be associated with machine scoring accuracy remains unknown. This study investigated how the features associated with the assessment construct of a scientific argumentation assessment item affected machine scoring performance. Specifically, we conceptualized the construct in three dimensions: complexity, diversity, and structure. We employed human experts to code characteristics of the assessment tasks and score middle school student responses to 17 argumentation tasks aligned to three levels of a validated learning progression of scientific argumentation. We randomly selected 361 responses to use as training sets to build machine-learning scoring models for each item. The scoring models yielded a range of agreements with human consensus scores, measured by Cohen’s kappa (mean = 0.60; range 0.38 − 0.89), indicating good to almost perfect performance. We found that higher levels ofComplexityandDiversity of the assessment task were associated with decreased model performance, similarly the relationship between levels ofStructureand model performance showed a somewhat negative linear trend. These findings highlight the importance of considering these construct characteristics when developing ML models for scoring assessments, particularly for higher complexity items and multidimensional assessments.
more »
« less
- Award ID(s):
- 2200757
- PAR ID:
- 10480435
- Publisher / Repository:
- Springer Science + Business Media
- Date Published:
- Journal Name:
- International Journal of Artificial Intelligence in Education
- Volume:
- 34
- Issue:
- 4
- ISSN:
- 1560-4292
- Format(s):
- Medium: X Size: p. 1482-1509
- Size(s):
- p. 1482-1509
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Abstract We systematically compared two coding approaches to generate training datasets for machine learning (ML): (i) a holistic approach based on learning progression levels and (ii) a dichotomous, analytic approach of multiple concepts in student reasoning, deconstructed from holistic rubrics. We evaluated four constructed response assessment items for undergraduate physiology, each targeting five levels of a developing flux learning progression in an ion context. Human-coded datasets were used to train two ML models: (i) an 8-classification algorithm ensemble implemented in the Constructed Response Classifier (CRC), and (ii) a single classification algorithm implemented in LightSide Researcher’s Workbench. Human coding agreement on approximately 700 student responses per item was high for both approaches with Cohen’s kappas ranging from 0.75 to 0.87 on holistic scoring and from 0.78 to 0.89 on analytic composite scoring. ML model performance varied across items and rubric type. For two items, training sets from both coding approaches produced similarly accurate ML models, with differences in Cohen’s kappa between machine and human scores of 0.002 and 0.041. For the other items, ML models trained with analytic coded responses and used for a composite score, achieved better performance as compared to using holistic scores for training, with increases in Cohen’s kappa of 0.043 and 0.117. These items used a more complex scenario involving movement of two ions. It may be that analytic coding is beneficial to unpacking this additional complexity.more » « less
-
Rapid advancements in computing have enabled automatic analyses of written texts created in educational settings. The purpose of this symposium is to survey several applications of computerized text analyses used in the research and development of productive learning environments. Four featured research projects have developed or been working on (1) equitable automated scoring models for scientific argumentation for English Language Learners, (2) a real-time, adjustable formative assessment system to promote student revision of uncertaintyinfused scientific arguments, (3) a web-based annotation tool to support student revision of scientific essays, and (4) a new research methodology that analyzes teacher-produced text in online professional development courses. These projects will provide unique insights towards assessment and research opportunities associated with a variety of computerized text analysis approaches.more » « less
-
Recent years have seen a movement within the research-based assessment development community towards item formats that go beyond simple multiple-choice formats. Some have moved towards free-response questions, particularly at the upper-division level; however, free-response items have the constraint that they must be scored by hand. To avoid this limitation, some assessment developers have moved toward formats that maintain the closed-response format, while still providing more nuanced insight into student reasoning. One such format is known as coupled, multiple response (CMR). This format pairs multiple-choice and multiple-response formats to allow students to both commit to an answer in addition to selecting options that correspond with their reasoning. In addition to being machine-scorable, this format allows for more nuanced scoring than simple right or wrong. However, such nuanced scoring presents a potential challenge with respect to utilizing certain testing theories to construct validity arguments for the assessment. In particular, Item Response Theory (IRT) models often assume dichotomously scored items. While polytomous IRT models do exist, each brings with it certain constraints and limitations. Here, we will explore multiple IRT models and scoring schema using data from an existing CMR test, with the goal of providing guidance and insight for possible methods for simultaneously leveraging the affordances of both the CMR format and IRT models in the context of constructing validity arguments for research-based assessments.more » « less
-
Few studies have compared Large Language Models (LLMs) to traditional Machine Learning (ML)-based automated scoring methods in terms of accuracy, ethics, and economics. Using a corpus of 1000 expert-scored and interview-validated scientific explanations derived from the ACORNS instrument, this study employed three LLMs and the ML-based scoring engine, EvoGrader. We measured scoring reliability (percentage agreement, kappa, precision, recall, F1), processing time, and explored contextual factors like ethics and cost. Results showed that with very basic prompt engineering, ChatGPT-4o achieved the highest performance across LLMs. Proprietary LLMs outperformed open-weight LLMs for most concepts. GPT-4o achieved robust but less accurate scoring than EvoGrader (~500 additional scoring errors). Ethical concerns over data ownership, reliability, and replicability over time were LLM limitations. EvoGrader offered superior accuracy, reliability, and replicability, but required, in its development a large, high-quality, human-scored corpus, domain expertise, and restricted assessment items. These findings highlight the diversity of considerations that should be used when considering LLM and ML scoring in science education. Despite impressive LLM advances, ML approaches may remain valuable in some contexts, particularly those prioritizing precision, reliability, replicability, privacy, and controlled implementation.more » « less
