An approach to the use of word embeddings in an opinion classification task

作者：

Highlights：

• Vector-based word representations can help to improve a document classifier.

• The information of word2vec vectors and bags of words are very complementary.

• The combination of word2vec and BOW word representations obtains the best results.

• Word2vec is much more stable than bag of words models in cross-domain experiments.

摘要

•Vector-based word representations can help to improve a document classifier.•The information of word2vec vectors and bags of words are very complementary.•The combination of word2vec and BOW word representations obtains the best results.•Word2vec is much more stable than bag of words models in cross-domain experiments.

论文关键词：Document classification,Opinion classification,Word embedding,Bag of words,Word2vec

论文评审过程：Received 23 June 2016, Revised 2 September 2016, Accepted 3 September 2016, Available online 5 September 2016, Version of Record 6 September 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.09.005