Graph-Based Lexical Networks for Technical Vocabulary Expansion in IoT-Enabled Education Platforms

The development of a number of Internet of Things (IoT)-enabled education platforms creates opportunities for flexible distribution of knowledge (in this context, technical vocabulary is fundamental to lexical knowledge acquisition). Lexical networks are a meaningful systematic process for modeling relationships among domain-specific vocabulary, so making sense of context and acquiring new vocabulary in its context through graph-based lexical networks can foster word meaning acquisition processes among students. The more traditional methods of vocational vocabulary acquisition, such as the use of static glossaries, or frequency-based extraction of terms from any technical document, are generally ill-suited as they do not capture or make relationships explicit, nor sustain a student's ability to keep pace with evolving technical disciplines or student specialization areas. The nuance of technical vocabulary related to the IoT creates a considerable challenge for learners who are trying to grasp the relationships among complex terms. Therefore, the paper introduces Graph-based Lexical Expansion Network for IoT education (GLEN-IoT), is a system that applies graph mining and natural language processing to generate semantic graphs from technical corpora. GLEN-IoT supports scalable and adaptive learning, which identifies clusters of related words, includes key nodes, and offers vocabulary recommendations based on context. The experimental findings demonstrated that the GLEN-IOT improved student recall, semantic coherence, and vocabulary coverage over baseline keyword extraction approaches. This study indicates that more engaged digital learning environments are created when there is method to overcome lexical gaps and encourage greater engage with IoT relevant knowledge.

Hali tarjima qilinmagan