Word2vec Feature Extraction in Traveler Comments Using Machine Learningin Imbalance Data
International Journal of Emerging Trends in Engineering Research · 2020
The tourism industry is one industry that utilizes promotion of product and services through Internet and web technology.One of the uses is on the tripadvisor website which provides a place for users to give their opinions on attractions, accommodations and hospitality.The opinion given is in the form of comments and ratings on a topic.This research was conducted to classify user comments on tourist objects to be in the form of rating on a scale of 1 to 5. The dataset used is user opinion data on the tripadvisor application with a total data of 17675.Word2vec is used to extract semantic features from words from the data they have.The data classification algorithms used in this study are random forest and SVM, and use the SMOTE and NearMiss handling imbalance techniques.The results showed that the utilization of random forest algorithms and SMOTE provided the best accuracy results with an accuracy of 82.11%, an average precision of 81.2% and an average F Score of 81.58%.