Semantic Embedding Model for Evaluating Writing Skills in Secondary
Abstract
Evaluating writing skills in secondary education requires accurate, automated approaches that capture both semantic meaning and linguistic quality. Traditional methods often rely on surface-level features such as grammar, vocabulary, or word count, which fail to assess deeper coherence and contextual relevance in student essays. Existing approaches struggle with subjectivity, limited generalization, and insufficient semantic understanding. To address these challenges, this study proposes a Semantic Embedding Model using a Siamese Neural Network (SNN) framework, which measures semantic similarity between student responses and reference texts. The model leverages contextual embeddings to effectively capture meaning, coherence, and writing quality beyond syntactic measures. The proposed method can be applied for essay grading, skill assessment, and providing feedback to students and educators. Experimental results demonstrate improved accuracy, fairness, and consistency in evaluating writing skills compared to traditional evaluation systems.