Advanced Educational Technology for Science Inquiry Assessment

Li, Haiying; Gobert, Janice D.; Graesser, Art; Dickler, Rachel

doi:10.1177/2372732218790017

Cited by 8 publications

(2 citation statements)

References 36 publications

(70 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, NGSS requires authentic and performance-based assessments (NRC, 2014), which demand both technology and novel forms of assessments, which might result in validity issues. For example, innovative assessments may use simulation or virtual reality to mock authentic scenarios and provide interactive platforms to examine students' use of scientific practices (Li et al 2018;Yoo and Kim 2014). Students' performance on the new forms of tests may be associated with not only their scientific knowledge, thinking, and practice but also their proficiency in using computers, which is of irrelevant interest in science assessments.…”

Section: Cognitive Validity: Targeting the Three-dimensionality Of Science Learningmentioning

confidence: 99%

On the Validity of Machine Learning-based Next Generation Science Assessments: A Validity Inferential Network

2021

View full text Add to dashboard Cite

This study provides a solid validity inferential network to guide the development, interpretation, and use of machine learningbased next-generation science assessments (NGSAs). Given that machine learning (ML) has been broadly implemented in the automatic scoring of constructed responses, essays, simulations, educational games, and interdisciplinary assessments to advance the evidence collection and inference of student science learning, we contend that additional validity issues arise for science assessments due to the involvement of ML. These emerging validity issues may not be addressed by prior validity frameworks developed for either non-science or non-ML assessments. We thus examine the changes brought in by ML to science assessments and identify seven critical validity issues of ML-based NGSAs: potential risk of misrepresenting the construct of interest, potential confounders due to that more variables may involve, nonalignment between interpretation and use of scores and designed learning goals, nonalignment between interpretation and use of scores and actual learning quality, nonalignment between machine scores and rubrics, limited generalizable ability of machine algorithmic models, and limited extrapolating ability of machine algorithmic models. Based on the seven validity issues identified, we propose a validity inferential network to address the cognitive, instructional, and inferential validity of ML-based NGSAs. To demonstrate the utility of this network, we present an exemplar of ML-based next-generation science assessments that was developed using a seven-step ML framework. We articulate how we used the validity inferential network to ensure accountable assessment design, as well as valid interpretation and use of machine scores.

show abstract

Section: Cognitive Validity: Targeting the Three-dimensionality Of Science Learningmentioning

confidence: 99%

On the Validity of Machine Learning-based Next Generation Science Assessments: A Validity Inferential Network

2021

View full text Add to dashboard Cite

show abstract

“…Research is one of the important components in a curriculum. As revealed by Li et al (2018), "To be educated as scientifically literate persons, students need to be appropriately assessed." To know someone educated or achieve the expected learning competencies, it is needed a scoring system.…”

Section: Introductionmentioning

confidence: 99%

Activities Assessment as a Tool to Measure Students’ Observation Skills in Science Learning

Dewanti¹

2019

SEAJ

View full text Add to dashboard Cite

Observation skills are one of the basic skills students must possess in science learning. Through observation skills, students are able to identify facts or initial knowledge before going on to the next stage of the science process skills. In science learning, student observation skills can be observed and measured through all learning activities both in the classroom and in the laboratory (practicum) by using the activity assessment sheet. Activity assessment sheet is a derivative form of performance assessment consisting of 1) student identity, 2) assessment instructions, 3) basic competencies, 4) assessment table (sub-material, observed observation skills, scores, and information), 5) formulation acquisition of final score, and 6) assessment rubric. The assessment sheet for this activity has been tested on 44 junior high school students and the average results reached more than 50% of students showing the highest score of observation skills. Thus, the activity assessment sheet can be said to be used to measure student observation skills.

show abstract

Learning Analytics for Assessing Hands-on Laboratory Skills in Science Classrooms Using Bayesian Network Analysis

et al. 2022

View full text Add to dashboard Cite

Advanced Educational Technology for Science Inquiry Assessment

Abstract: Computer-based techniques, such as educational data mining and natural language processing, allow for automatically scoring science inquiry competencies and the facilitation of personalized instruction and tutoring that adapt to individual students.

Cited by 8 publications

References 36 publications

On the Validity of Machine Learning-based Next Generation Science Assessments: A Validity Inferential Network

On the Validity of Machine Learning-based Next Generation Science Assessments: A Validity Inferential Network

Activities Assessment as a Tool to Measure Students’ Observation Skills in Science Learning

Learning Analytics for Assessing Hands-on Laboratory Skills in Science Classrooms Using Bayesian Network Analysis

Contact Info

Product

Resources

About