Aug 2026· Journal of Visualized Experiments· Vol 234· 0 citations
Medicine
TL;DR
A hierarchical transfer training system based on the DeepSeek model covering four progressive task tiers covering four progressive task tiers, with all tasks defined in triple form, is constructed to address the limitation that traditional English writing instruction neglects systematic cultivation of language transfer.
Abstract
To address the limitation that traditional English writing instruction neglects systematic cultivation of language transfer and existing prompt frameworks fail to fit classroom teaching, this study constructs a hierarchical transfer training system based on the DeepSeek model covering four progressive task tiers: sentence, paragraph, discourse, and culture, with all tasks defined in triple form. A five-dimensional task library covering syntax, structure, culture, register, and logic is established, and targeted prompts are automatically generated from students' authentic writing drafts. Integrated with the model's Mixture of Experts (MoE) architecture, a nested prompt chain is developed to split complicated assignments into three sequential phases: semantic reorganization, linguistic revision, and cultural adaptation. Adopting a quasi-experimental design, this research recruits 60 second-year English majors from one university and assigns them to an experimental group and a control group of 30 students each for three weeks of staged intervention across three training rounds. Post-experiment results reveal that the experimental group's cultural transfer score rises from 2.8 to 4.5, compared with a mere 0.3 increment in the control group; its average teacher-assessed score improves from 59.1 to 74.4, compared with the control group's increase from 60.1 to 64.9. Most correlation coefficients between AI scoring and teacher evaluation exceed 0.8, and over 90% participants approve of the AI rewriting and structural optimization functions. Due to the small sample size in this trial, this optimization approach is feasible for implementation in university English writing classes.
Considering pre-service teachers’ dual identity as both “learners” and “future teachers,” the paper explores pathways for developing their writing learning and teaching competencies in the AI era.
Wenhuan Sun· International Journal of Edu...· 0 citations
This study examines the effectiveness of writing conferences as a supplementary instructional feedback approach for addressing first language (L1) negative transfer errors in English writing. Drawing on theoretical frameworks from second language acquisition and writing pedagogy, the study focuses on three categories of L1 transfer errors: semantic, syntactic, and capitalization. The study argues that written corrective feedback alone is insufficient to help students understand and self-correct systematic errors, positioning oral, face-to-face conferencing as a necessary complement. Using a mixed-methods design, the study investigates how writing conferences conducted by a shared-L1 instructor improve writing accuracy and support sustained metalinguistic awareness across new writing tasks. Participants were 40 female first-year Saudi undergraduates at a public university in Saudi Arabia who were learners of English as a foreign language (EFL) and whose first language was Arabic. Their writing was tracked across three writing tasks over one semester, using a convergent parallel design. An experimental group (n = 20) received written corrective feedback followed by individual writing conferences, whereas a control group (n = 20) received written corrective feedback only. Results showed statistically significant and sustained reductions in all three error categories for the experimental group across tasks of increasing unfamiliarity. Thematic analysis of interviews revealed three themes: enhanced metalinguistic understanding, reduced writing anxiety, and explicit L1 transfer awareness. These findings suggest that shared-L1 conferencing promotes qualitatively different learning from written feedback alone, and offers a pedagogically applicable model for L1-informed writing instruction in EFL contexts.
A. Saaty· Journal of Education and Lea...· 0 citations
The
Multi-Tiered System of Support
(MTSS) is a preventive framework that has demonstrated its effectiveness in early literacy instruction. However, its applicability to foreign language writing teaching has yet to be explored. The present study aims to address this educational shortcoming. A total of 132 students from fourth, fifth, and sixth grades of primary education were asked to write a narrative in English as a foreign language (EFL). The texts were analyzed according to the types of errors produced. This enabled four distinct writing profiles to be identified, corresponding to the tiers of support within the MTSS: Strong Writers (47.73%, Tier 1), Grammar-Weak Writers (32.58%, Tier 2), Spelling-Weak Writers (12.88%, Tier 2), and Poor Writers (6.82%, Tier 3). These findings suggest that the MTSS model can be effectively adapted to narrative writing instruction in EFL contexts. Furthermore, in the absence of standardized assessment tools, analyzing errors in written narratives could provide a practical method for categorizing students into these tiers. Finally, the study outlines key considerations for implementing MTSS in this context. It offers guidance for applying evidence-based intervention strategies across different levels of support. Here you can access a
video summary
and an
infographic
of the article, both generated with NotebookLM.
Uxue Pérez-Litago, Cristina Martínez‐García, Carmen Hevia-Tuero et al.· Reading & Writing· 0 citations
In non-native English classrooms, multimedia resources often produce a cognitive gap of high input but low output: visual contexts and target-language forms fail to form stable semantic connections. To address this problem, this study proposes a three-stage multimedia teaching strategy of context anchoring, modal verification, and output transfer. First, a micro-context video library is constructed using word-vector semantic association, with target vocabulary anchoring the semantic field while 12-second clips control cognitive load. Second, a semi-structured virtual dialogue agent dynamically triggers recast and clarification feedback according to learners’ spoken output, grammar breaks, and pragmatic deviations. Third, digital narrative reconstruction tasks require learners to convert video-based semantic information into written storyboards, promoting cross-modal syntactic transfer. Experiments show that the semantic priming effect size increases to 145.2 ms, speech-flow break density decreases to 12.3, and average clause nesting depth rises to 1.89. The framework turns multimedia into a cognitive scaffold and is compatible with networked multimedia transmission, wireless interactive classrooms, and electromagnetic-safe digital learning spaces.
Juan Wu, Yingying Du, Xiaohui Zhang et al.· Advanced Electromagnetics· 0 citations
: This study focuses on the construction of personalized English writing feedback mechanism driven by artificial intelligence, which breaks through the limitation that existing automatic writing evaluation tools only focus on surface language form error correction, and proposes a four-layer system architecture (data layer, processing layer, strategy engine layer and interaction layer). In this study, a three-level differentiated feedback model based on students' level (L1 basic level, L2 development level and L3 proficiency level) is designed, which combines the wrong "fingerprint" strengthening strategy and metacognitive excitation mechanism to guide students to correct themselves instead of directly providing answers. At the same time, a three-stage teacher-AI collaborative process is constructed to retain the core value of teachers in complex content evaluation and emotional support. Through an 8-week quasi-experimental study of two parallel classes (60 students in total) in Grade Two of a middle school, the results show that the post-test writing performance of the experimental group is significantly higher than that of the control group (t=5.67, p<0.01), with an average increase of 4.34 points. The recurrence rate of high-frequency errors in the experimental group was significantly lower than that in the control group (P < 0.05). The feedback viewing rate of students reached 94.2%, and the revised adoption rate reached 76.8%, and the students with weak foundation (L1 layer) made the most obvious progress. The research shows that the AI-driven personalized feedback mechanism can effectively improve students' writing performance, reduce the error recurrence rate and enhance students' active revision behavior, which provides a feasible technical path and practical paradigm for the digital transformation of foreign language education.
Ying Zhai· International Journal of New...· 0 citations
Generative artificial intelligence is increasingly used to create English as a Foreign Language (EFL) reading materials, yet fluent output may still simplify cultural groups. This study compared 24 classroom-oriented passages generated by ChatGPT GPT-5.6 and DeepSeek-V4 from 12 identical prompts submitted on 22 July 2026. Each prompt requested a 220–250-word intermediate-level passage representing Chinese, Pakistani, and mainstream English-speaking Western perspectives fairly. Directed qualitative content analysis examined inclusion, balance, intragroup variation, specificity, essentialization, the collectivist-individualist binary, evaluative hierarchy, stereotyping risk, intercultural sensitivity, and prompt compliance. ChatGPT produced 2,763 words and met the requested range in all 12 passages. DeepSeek produced 3,095 words and met the requested range in five passages. Both systems included the three perspectives and promoted respectful communication. ChatGPT used more qualifications and acknowledged internal variation more consistently. DeepSeek supplied more named cultural detail but relied more often on broad contrasts that framed Chinese and Pakistani contexts as collective and Western contexts as individualistic. The findings show that cultural inclusion does not ensure balanced representation. The proposed review criteria help teachers and curriculum developers evaluate variation, specificity, stereotyping risk, and classroom suitability before using AI-generated materials.
Idrees, Liu Yongzhi· International "Journal of Ac...· 0 citations