Research on automatic evaluation algorithm of subjective questions based on vector space model and synonym lexical forest

Abstract

Word2vec word vector algorithm and Doc2vec text vectoring algorithm calculate the similarity between words and between texts from the perspective of vector space without considering the semantic similarity between texts. Thus, in this paper, an automatic evaluation algorithm is proposed to combine semantic similarity based on synonym lexical forest and text similarity based on vector space. Meanwhile, Sentiment analysis was used to obtain the emotional score of the reference answers and students answers in the subjective questions. Finally, the final score of students answers was obtained by combining text similarity and emotion scores. In this paper, logistics professional education is the experimental object of the experiment. The experimental results show that the algorithm has achieved good scoring results.