Impact of automated scoring on interpreting performance and self-regulated learning: evidence from a pedagogical experiment
Chen Chen e outros, 2026 · Frontiers in Psychology
Providing automated scoring and immediate diagnostic feedback during weekly practice improved student interpreting test scores by 1.03 standard deviations compared to traditional delayed teacher feedback.
Estimativa · interpreting test score, standardized mean difference (Cohen's d)
1,03 [0,410; 1,64]
standardized mean difference (Cohen's d)
p = 0.001
- Desenho
- Outro observacional. Quasi-experiment with two intact classes
- População
- Sophomores majoring in English Translation and Interpreting at a normal university in central China
- Amostra
- 46 · students across 2 classes
Onde está o número
Results > Effects on interpreting performance > Overall changes in performance; Section 4.1.1, paragraph 3 (and Table 2, row 'Post-test')
At post-test the experimental group (M = 85.58, SD = 5.07) scored higher than the control group (M = 80.84, SD = 4.01), t(44) = 3.50, p = 0.001, d = 1.03, 95% CI [0.41, 1.64] (Table 2).
Contexto
What changed: Students in the experimental group used the Yunyi AI scoring system for after-class interpreting practice, receiving immediate automated scores and diagnostic feedback for 14 weeks. Comparison: Control group students practiced the same materials and received conventional delayed collective teacher feedback. Limits: Small quasi-experimental sample of two intact classes (N=46) at a single university, with proprietary scoring algorithms and gains concentrated in linguistic form rather than meaning transfer.
Caminho no grafo
- FamíliaInformação e persuasão
- TipoCapacitação e aconselhamento
- MecanismoAprendizagem assistida por computador
- ResultadoAprendizado (proficiência em testes)
- EixoEducação
MAGI só cita evidência deste instrumento
Lugares do estudo
- China · País · CN
- Licença
- CC-BY
- Revisão
- Extraído por máquina, não revisadoExtraído por: gemini-3.8-flash, 2026-10-23