From: Sentiment analysis of Indonesian datasets based on a hybrid deep-learning strategy
Publication | Technique applied | Claimed outcome | Limitations |
---|---|---|---|
[21] | TF-IDF as text vectorization and the stochastic gradient descent (SGD) as the classifier | The proposed technique obtained an accuracy of 81,726% | Not achieving superior accuracy due to its simplicity in the proposed scheme |
Sentiment classification of reviews using BERT and Softmax | Pre-training language model outperforms lexicon-based and review rating schemes | Not achieving superior accuracy due to its simplicity in the proposed scheme |