Comparison of Modeling Time of Word Vector Methods

In this study, two different datasets for sentiment analysis have been modeled by Word2Vec that it is a word vector algorithm. While the model is creating that has used two different methods CBoW and Skip-Gram of Word2Vec. Generally, the arithmetic mean is used for modeling a text with Word2Vec. In this study, three different methods for modeling a text are suggested on both CBoW and Skip-Gram. Its modeling time (training time) is measured. As a result, it was experimentally shown that CBoW is more successful than Skip-Gram based for modeling time