Artificial intelligence in history education. Linguistic content and complexity analyses of student writings in the CAHisT project (Computational assessment of historical thinking)

Bertram, Christiane; Weiß, Zarah; Zachrich, Lisa; Ziai, Ramon

doi:10.1016/j.caeai.2021.100038

Cited by 14 publications

(8 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the material process comes to the behavioral process, the second most common process type in students' narrative writings. During this procedure, the students' narrative texts depicted a variety of physiological and psychological behaviors (usually human) (Bertram et al, 2021;Jiang et al, 2019). They are in the middle of mental and physical processes.…”

Section: Discussionmentioning

confidence: 99%

Transitivity Analysis of EFL Students’ Narrative Text in Vocational High School

Agustina

Suarnajaya

2021

JPBI

View full text Add to dashboard Cite

Language cannot be understood one at a time without considering contextual information about the current circumstances and culture. As a result, language can only be understood when individuals comprehend the circumstance and culture. This study aimed at identifying the process types that characterize the students' narrative texts. This study applied a descriptive qualitative method. The researcher collected the data from narrative texts. There were 28 students selected to be the subjects of this study. The collected data, presented in sentences and clauses, were analyzed using Halliday's transitivity system. Findings show that the process type that are dominantly used in the students' narrative texts are material, behavioral, intensive attributive, verbal, mental, and existential processes. The material process was the most common process type used because the students' subjects were connected to past figures. The findings in this study of the students' narrative texts demonstrate that the students must use the linguistic elements of a narrative text to give information. The purpose of text types in students' narrative texts is to encourage readers to imagine the words and sentence patterns used in the texts. It may help to minimize misunderstandings about the contents of the narrative text. As a result, while creating a narrative text, the students must employ the proper specific meaning, generic structure, linguistic characteristics, and language elements to stimulate readers' interest in providing necessary information while entertaining them.

show abstract

Section: Discussionmentioning

confidence: 99%

Transitivity Analysis of EFL Students’ Narrative Text in Vocational High School

Agustina

Suarnajaya

2021

JPBI

View full text Add to dashboard Cite

show abstract

“…However, CT as a guide of belief and action (Gyenes, 2021) is an important ability for college students in all fields (Davies, 2013;Zhang et al, 2022). In humanities subjects, research has shown that independent thinking skills are valuable indicators of students' discipline-specific abilities in humanities subjects (Bertram et al, 2021). College students in the humanities need CT abilities to identify problems and find critical solutions (Baş et al, 2022).…”

Section: Discussionmentioning

confidence: 99%

Constructing a critical thinking evaluation framework for college students majoring in the humanities

Tang

Geng

et al. 2022

Front. Psychol.

View full text Add to dashboard Cite

IntroductionEducation for sustainable development (ESD) has focused on the promotion of sustainable thinking skills, capacities, or abilities for learners of different educational stages. Critical thinking (CT) plays an important role in the lifelong development of college students, which is also one of the key competencies in ESD. The development of a valuable framework for assessing college students’ CT is important for understanding their level of CT. Therefore, this study aimed to construct a reliable self-evaluation CT framework for college students majoring in the humanities.MethodsExploratory factor analysis (EFA), confirmatory factor analysis (CFA), and Item analysis were conducted to explore the reliability and validity of the CT evaluation framework. Six hundred and forty-two college students majoring in the humanities were collected. The sample was randomly divided into two subsamples (n1 = 321, n2 = 321).ResultsThe Cronbach’s alpha coefficient for the whole scale was 0.909, and the values of the Cronbach’s alpha coefficients for individual factors of the scale ranged from 0.724 to 0.878. Then CFA was conducted within the scope of the validity study of the scale. In this way, the structure of the 7-factor scale was confirmed. Results indicated that the constructed evaluation framework performed consistently with the collected data. CFA also confirmed a good model fitting of the relevant 22 factors of the college students’ CT framework (χ2/df = 3.110, RMSEA = 0.056, GFI = 0.927, AGFI = 0.902, NFI = 0.923, and CFI = 0.946).DiscussionThese findings revealed that the CT abilities self-evaluation scale was a valid and reliable instrument for measuring the CT abilities of college students in the humanities. Therefore, the college students’ CT self-evaluation framework included three dimensions: discipline cognition (DC), CT disposition, and CT skills. Among them, CT disposition consisted of motivation (MO), attention (AT), and open-mindedness (OM), while CT skills included clarification skills (CS), organization skills (OS), and reflection (RE). Therefore, this framework can be an effective instrument to support college students’ CT measurement. Consequently, some suggestions are also put forward regarding how to apply the instrument in future studies.

show abstract

“…We chose this system, because it is to our knowledge the most extensive available analysis system for German. The underlying feature extraction engine for German has proven highly successful and robust in a variety of education-related tasks including readability assessment (Weiss and Meurers, 2018;Kühberger et al, 2019) and work linked to writing quality assessment (Weiss and Meurers, 2019a,b;Weiss et al, 2019;Bertram et al, 2021;Riemenschneider et al, 2021). Also, using a publicly available web-based system increases the re-usability of any model using these features in practice.…”

Section: Spotlight-dementioning

confidence: 99%

Assessing sentence readability for German language learners with broad linguistic modeling or readability formulas: When do linguistic insights make a difference?

Weiß¹,

Meurers²

2022

Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)

Self Cite

View full text Add to dashboard Cite

The paper presents a new state-of-the-art sentence-wise readability assessment model for German L2 readers. We build a linguistically broadly informed machine learning model and compare its performance against four commonly used readability formulas. To understand when the linguistic insights used to inform our model make a difference for readability assessment and when simple readability formulas suffice, we compare their performance based on two common automatic readability assessment tasks: predictive regression and sentence pair ranking. We find that leveraging linguistic insights yields top performances across tasks, but that for the identification of simplified sentences also readability formulas -which are easier to compute and more accessible -can be sufficiently precise. Linguistically informed modeling, however, is the only viable option for high quality outcomes in finegrained prediction tasks.We then explore the sentence-wise readability profile of leveled texts written for language learners at a beginning, intermediate, and advanced level of German. Our findings highlight that a texts' readability is driven by the maximum rather than the overall readability of sentences. This has direct implications for the adaptation of learning materials and showcases the importance of studying readability also below the document level.

show abstract

Artificial intelligence in history education. Linguistic content and complexity analyses of student writings in the CAHisT project (Computational assessment of historical thinking)

Cited by 14 publications

References 37 publications

Transitivity Analysis of EFL Students’ Narrative Text in Vocational High School

Transitivity Analysis of EFL Students’ Narrative Text in Vocational High School

Constructing a critical thinking evaluation framework for college students majoring in the humanities

Assessing sentence readability for German language learners with broad linguistic modeling or readability formulas: When do linguistic insights make a difference?

Contact Info

Product

Resources

About