EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Personalized English learning path planning engine based on knowledge graph

Yingying Ma, Jiachen Gao

Data and Metadata · 13.03.2026 · 5 · 796

DOI: 10.56294/dm2026796 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Data and Metadata, online erschienen am 13.03.2026. Verfasst von Yingying Ma und 1 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction:[Rev1.1] The transformation of traditional English language teaching into intelligent AI-based systems represents a significant shift in contemporary education. Adaptive, data-driven technologies are replacing outdated methods reliant on grammar translation and rote memorization. This research investigates how Artificial Intelligence (AI) tools are reshaping English language learning and teaching by offering personalized, feedback-driven, and interactive experiences.Methods[Rev2.1]: Utilizing a mixed-method design, the study involved a control group employing traditional teaching practices and an experimental group utilizing AI-based tools, including Natural Language Processing (NLP), writing assistants, speech recognition modules, and chatbot-based conversation tutors. A total of 356 participants, consisting of instructors, provided data for comparison between traditional methods and AI-assisted instruction.Results: [Rev3.1]The effectiveness of AI in enhancing instructional efficiency, feedback quality, and overall teaching performance was assessed through quantitative measures, such as performance analytics and teaching outcomes, as well as qualitative insights from interviews and surveys. Descriptive statistics revealed that the experimental group achieved significantly higher scores in Pronunciation Accuracy (PA) (81,6[Rev4.1]). Independent sample t-tests confirmed substantial improvements in PA (t = -8,21, p < 0,001). Multiple regression analysis indicated a positive relationship with Contextual Comprehension (CC) (β = 0,22, t = 5,12), while Pearson correlation analysis demonstrated that Vocabulary Acquisition (VA) exhibited the strongest positive association with other variables (r = 0,71). The data were analyzed using SPSS software (version 27,0).Conclusions: [Rev5.1]The findings illustrated notable advancements in pronunciation, vocabulary, and comprehension, alongside increased motivation and retention among learners. Instructors reported a reduced workload and more accurate assessments. Overall, AI serves as an intelligent support system that enhances interaction and personalization in the learning process, all while preserving the essential role of the teacher.

Zitieren

APA

Ma, Y., & Gao, J. (2026). Personalized English learning path planning engine based on knowledge graph. Data and Metadata, 5, 796. https://doi.org/10.56294/dm2026796

Vancouver

Ma Y, Gao J. Personalized English learning path planning engine based on knowledge graph. Data and Metadata. 2026;5:796. doi:10.56294/dm2026796

BibTeX
@article{Ma2026,
  author = {Ma, Yingying and Gao, Jiachen},
  title = {Personalized English learning path planning engine based on knowledge graph},
  journal = {Data and Metadata},
  year = {2026},
  volume = {5},
  pages = {796},
  doi = {10.56294/dm2026796}
}
Kostenlos starten →