Sentiment Analysis Using Word2vec And Long Short-Term Memory (LSTM) For Indonesian Hotel Reviews

Citations Over TimeTop 1% of 2021 papers

Abstract

Generally, Online Travel Agent (OTA) has a review element where clients can give reviews of the facilities they have used. Availability of a huge volume of reviews makes it troublesome for service executives to know the percent of reviews that have an effect on their services. Thus, it is essential to develop a sentiment assessment technique with respect to hotel reviews, particularly in Indonesian language. This research makes use of Long-Short Term Memory (LSTM) model as well as the Word2Vec model. The integration of Word2Vec and LSTM variables used in this research are Word2Vec architecture, Word2Vec vector dimension, Word2Vec evaluation method, pooling technique, dropout value, and learning rate. On the basis of an experimental research performed through 2500 review texts as dataset, the best performance was obtained that had accuracy of 85.96%. The parameter combinations for Word2Vec are Skip-gram as architecture, Hierarchical Softmax as evaluation method, and 300 as vector dimension. Whereas the parameter combinations for LSTM are dropout value is 0.2, pooling type is average pooling, and learning rate is 0.001.

Related Papers

• → Max-Pooling Dropout for Regularization of Convolutional Neural Networks(2015)173 cited
• → Multi‐scale feature fusion network for person re‐identification(2020)9 cited
• → Exploring Alternatives to Softmax Function(2021)1 cited
• → Max-Pooling Dropout for Regularization of Convolutional Neural Networks(2015)20 cited