An official website of the United States government
Automated methods are becoming increasingly used to support formative feedback on students’ science explanation writing. Most of this work addresses students’ responses to short answer questions. We investigate automated feedback on students’ science explanation essays, which discuss multiple ideas. Feedback is based on a rubric that identifies the main ideas students are prompted to include in explanatory essays about the physics of energy and mass. We have found that students revisions generally improve their essays. Here, we focus on two factors that affect the accuracy of the automated feedback. First, learned representations of the six main ideas in the rubric differ with respect to their distinctiveness from each other, and therefore the ability of automated methods to identify them in student essays. Second, sometimes a student’s statement lacks sufficient clarity for the automated tool to associate it more strongly with one of the main ideas above all others.
more »
« less
Introduction to Focus Section: Computational Perspectives in the History of Science
Digital technologies have transformed both the historical record and the historical profession. This Focus section examines how computational methods have influenced, and will influence, the history of science. The essays discuss the new types of questions and narratives that computational methods enable, and the need for better data management in the HPS community. They showcase various methodological approaches, including textual and network analyses, and they place the computational turn in historiographical and societal context. Rather than surrender to technophilia or technophobia, the essays articulate both the benefits and the drawbacks of computational HPS. They agree that the future of the field depends on the successful integration of technological developments, social practices, and infrastructural support, and that historians of science must learn to embrace collaboration both within and beyond disciplinary boundaries.
more »
« less
- Award ID(s):
- 1734236
- PAR ID:
- 10093200
- Date Published:
- Journal Name:
- Isis
- Volume:
- 110
- Issue:
- 3
- ISSN:
- 0021-1753
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Many researchers insist that computational methods will transform the historical profession, while an equally large number reject these claims as unwarranted hype. In this study, we attempt to place the debate in historical and social context. The article is divided into three parts. The first part offers a brief review of computational history. We ask whether the “computational turn” bears any resemblance to quantitative history, and how it fits within the digital humanities. The second part describes our recent attempts to apply computational methods to an existing project in the history of science using a standardized workflow. We demonstrate that each step of the workflow adds another layer of subjectivity. The third part reflects on what computational methods mean for the historical profession. We systematically review the positive aspects of computational history (open access, interdisciplinary collaboration, and new perspectives) as well as the negative aspects (inequality, fragility, and the threat of automation), and we offer prescriptions based on our experiences.more » « less
-
null (Ed.)Abstract Ribonucleoprotein (RNP) granules are membraneless organelles (MLOs), which majorly consist of RNA and RNA-binding proteins and are formed via liquid–liquid phase separation (LLPS). Experimental studies investigating the drivers of LLPS have shown that intrinsically disordered proteins (IDPs) and nucleic acids like RNA and other polynucleotides play a key role in modulating protein phase separation. There is currently a dearth of modelling techniques which allow one to delve deeper into how polynucleotides play the role of a modulator/promoter of LLPS in cells using computational methods. Here, we present a coarse-grained polynucleotide model developed to fill this gap, which together with our recently developed HPS model for protein LLPS, allows us to capture the factors driving protein-polynucleotide phase separation. We explore the capabilities of the modelling framework with the LAF-1 RGG system which has been well studied in experiments and also with the HPS model previously. Further taking advantage of the fact that the HPS model maintains sequence specificity we explore the role of charge patterning on controlling polynucleotide incorporation into condensates. With increased charge patterning we observe formation of structured or patterned condensates which suggests the possible roles of polynucleotides in not only shifting the phase boundaries but also introducing microscopic organization in MLOs.more » « less
-
As use of artificial intelligence (AI) has increased, concerns about AI bias and discrimination have been growing. This paper discusses an application called PyrEval in which natural language processing (NLP) was used to automate assessment and pro- vide feedback on middle school science writing with- out linguistic discrimination. Linguistic discrimination in this study was operationalized as unfair assess- ment of scientific essays based on writing features that are not considered normative such as subject- verb disagreement. Such unfair assessment is espe- cially problematic when the purpose of assessment is not assessing English writing but rather assessing the content of scientific explanations. PyrEval was implemented in middle school science classrooms. Students explained their roller coaster design by stat- ing relationships among such science concepts as potential energy, kinetic energy and law of conser- vation of energy. Initial and revised versions of sci- entific essays written by 307 eighth- grade students were analyzed. Our manual and NLP assessment comparison analysis showed that PyrEval did not pe- nalize student essays that contained non-normative writing features. Repeated measures ANOVAs and GLMM analysis results revealed that essay quality significantly improved from initial to revised essays after receiving the NLP feedback, regardless of non- normative writing features. Findings and implications are discussed.more » « less
-
As use of artificial intelligence (AI) has increased, concerns about AI bias and discrimination have been growing. This paper discusses an application called PyrEval in which natural language processing (NLP) was used to automate assessment and pro- vide feedback on middle school science writing with- out linguistic discrimination. Linguistic discrimination in this study was operationalized as unfair assess- ment of scientific essays based on writing features that are not considered normative such as subject- verb disagreement. Such unfair assessment is espe- cially problematic when the purpose of assessment is not assessing English writing but rather assessing the content of scientific explanations. PyrEval was implemented in middle school science classrooms. Students explained their roller coaster design by stat- ing relationships among such science concepts as potential energy, kinetic energy and law of conser- vation of energy. Initial and revised versions of sci- entific essays written by 307 eighth- grade students were analyzed. Our manual and NLP assessment comparison analysis showed that PyrEval did not pe- nalize student essays that contained non-normative writing features. Repeated measures ANOVAs and GLMM analysis results revealed that essay quality significantly improved from initial to revised essays after receiving the NLP feedback, regardless of non- normative writing features. Findings and implications are discussed.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- The DOI is not currently available.
