Classification of Tourist Comment Using Word2vec and Random Forest Algorithm
Classification of Tourist Comment Using Word2vec and Random Forest Algorithm

Summary/Abstract: Text classification is one of the ways to classify sentences. The grouped data are comments from social media with training data from sites that provide points /scores for each review given such as tripadvisor.co.id. The word2vec method is used to extract words into numbers so that the machine learning algorithm can be applied to classify data. Word2vec is an unsupervised task that is capable of utilizing unlabeled data to convert a word into its vector representation that can also find the semantic relationship between words by counting their distance. The goal from this paper is that data from social media such as Twitter or Instagram can also quickly find out the total /weight of a tourist place from the comment given. The experiment shows that the result of F1 Score on data without removing stop words and eliminate the train data, give a better result 0,85.

• Details
• Contents