Journal of Computational Methods in Sciences and Engineering, Journal Year: 2024, Volume and Issue: 25(2), P. 1210 - 1222

Published: Nov. 8, 2024

Nowadays, English teachers have more options to improve curriculum development through the rapid rise of textual data from feedback, student interactions, and educational resources. This study introduces a novel Intelligent Mined Text-Hierarchical Dirichlet Process Modelling + Quantitative Term-Frequency Matrix (IMT-HDPM QTFM) methodology that effectively integrates topic modeling text mining techniques enhance refine understanding key language instruction themes concepts. proposes enables teaching methods in-depth analysis. The dataset was gathered various sources, including lessons, essays, exercises, categorized by difficulty level (Easy, Medium, Hard), with each entry containing brief sample, source, category. IMTs are cleansing, tokenization, stop word removal, stemming/lemmatization, which used for removing punctuation, numbers, special characters, common words sample build cleaned data. HDPM provides flexible probabilistic framework enhances capture distributions across documents, leading accurate identification meaningful topics. QTFM examines how topics relate other in IMT-HDPM resulted most significantly improved concepts texts then reduced time spent on manual refinement. evaluation metrics included accuracy (94%), recall (95%), precision (96%), indicating robustness proposed methodology. analyzes unstructured blogs, social networks, forums; important trends insights can be extracted variety online content, improving comprehension platforms.

Language: Английский