A Method of Detecting Run-on Essays Based on the Degree of Tangency

This study proposes a method to detect whether an essay is off-topic or not based on the degree of tangency, because of the lack of accurate and efficient algorithms for off-topic detection in domestic essay-assisted grading systems. This study uses the LDA topic model to extract the topic in the set of topic requirements and reference essays and extracts the topic words of the essays to be evaluated, based on which the proposed method of calculating the topic degree is used to calculate the topic degree, to measure the relevance of the essays to the topic, and finally filter the runaway essays by setting a reasonable threshold. The experimental results show that this method is more effective than the traditional TF-IDF algorithm based on the vector space model and can detect more run-on essays, and the accuracy rate is higher, with the F value reaching over 90%, which achieves the intelligent processing of essay run-on detection and can be effectively applied in English composition teaching.