An official website of the United States government
The Next Generation Science Standards (NGSS) emphasize integrating three dimensions of science learning: disciplinary core ideas, cross-cutting concepts, and science and engineering practices. In this study, we develop formative assessments that measure student understanding of the integration of these three dimensions along with automated scoring methods that distinguish among them. The formative assessments allow students to express their emerging ideas while also capturing progress in integrating core ideas, cross-cutting concepts, and practices. We describe how item and rubric design can work in concert with an automated scoring system to independently score science explanations from multiple perspectives. We describe item design considerations and provide validity evidence for the automated scores.
more »
« less
Identifying NGSS-Aligned Ideas in Student Science Explanations
With the increasing use of online interactive environments for science and engineering education in grades K-12, there is a growing need for detailed automatic analysis of student explanations of ideas and reasoning. With the widespread adoption of the Next Generation Science Standards (NGSS), an important goal is identifying the alignment of student ideas with NGSS-defined dimensions of proficiency. We develop a set of constructed response formative assessment items that call for students to express and integrate ideas across multiple dimensions of the NGSS and explore the effectiveness of state-of-the-art neural sequence-labeling methods for identifying discourse-level expressions of ideas that align with the NGSS. We discuss challenges for idea detection task in the formative science assessment context.
more »
« less
- Award ID(s):
- 1812660
- PAR ID:
- 10184621
- Date Published:
- Journal Name:
- Workshop on Artificial Intelligence for Education (AI4EDU@AAAI)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The Next Generation Science Standards (NGSS) reflect an ambitious vision for science education where students investigate phenomena or solve problems through using and applying disciplinary core ideas in concert with science and engineering practices and crosscutting concepts. Because the NGSS are so different from prior standards, the need for high-quality curriculum materials is especially great. As new curricula go to scale, it will be important to conduct evidence-based research on their efficacy. We conducted a randomized experiment to examine the efficacy of a widely available NGSS-designed middle school curriculum for improving seventh grade students’ learning in physical science. A hierarchical linear modeling approach was applied to analyze student learning outcomes as measured by an NGSS-aligned assessment. Initial findings demonstrate evidence of promise of the curriculum materials for supporting three-dimensional teaching and learning. The findings provide support for further research on NGSS-designed materials at other grade levels and within other science domains.more » « less
-
With the widespread adoption of the Next Generation Science Standards (NGSS), science teachers and online learning environments face the challenge of evaluating students' integration of different dimensions of science learning. Recent advances in representation learning in natural language processing have proven effective across many natural language processing tasks, but a rigorous evaluation of the relative merits of these methods for scoring complex constructed response formative assessments has not previously been carried out. We present a detailed empirical investigation of feature-based, recurrent neural network, and pre-trained transformer models on scoring content in real-world formative assessment data. We demonstrate that recent neural methods can rival or exceed the performance of feature-based methods. We also provide evidence that different classes of neural models take advantage of different learning cues, and pre-trained transformer models may be more robust to spurious, dataset-specific learning cues, better reflecting scoring rubrics.more » « less
-
null (Ed.)With the widespread adoption of the Next Generation Science Standards (NGSS), science teachers and online learning environments face the challenge of evaluating students’ integration of different dimensions of science learning. Recent advances in representation learning in natural language processing have proven effective across many natural language processing tasks, but a rigorous evaluation of the relative merits of these methods for scoring complex constructed response formative assessments has not previously been carried out. We present a detailed empirical investigation of feature-based, recurrent neural network, and pre-trained transformer models on scoring content in real-world formative assessment data. We demonstrate that recent neural methods can rival or exceed the performance of feature-based methods. We also provide evidence that different classes of neural models take advantage of different learning cues, and pre-trained transformer models may be more robust to spurious, dataset-specific learning cues, better reflecting scoring rubrics.more » « less
-
In principle, educators can use writing to scaffold students’ understanding of increasingly complex science ideas. In practice, formative assessment of students’ science writing is very labor intensive. We present PyrEval+CR, an automated tool for formative assessment of middle school students’ science essays. It identifies each idea in a student’s science essay, and its importance in the curriculum.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
