Key word extraction for short text via word2vec, doc2vec, and textrank

Abstract

The rapid development of social media encourages people to share their opinions and feelings on the Internet.Every day, a large number of short text comments are generated through Twitter, microblogging, WeChat, etc., andthere is high commercial and social value in extracting useful information from these short texts. At present, moststudies have focused on extracting text key words. For example, the LDA topic model has good performance with longtexts, but it loses effectiveness with short texts because of the noise and sparsity problems. In this paper, we attempt touse Word2Vec and Doc2Vec to improve short-text key word extraction. We first added the method of the collaborativetraining of word vectors and paragraph vectors and then used the TextRank model’s clustering nodes. We adjusted theweights of the key words that were generated by computing the jump probability between nodes and then obtained thenode-weighted score, and eventually sorted the generated key words. The experimental results show that the improvedmethod has good performance on the datasets.