What type of study is this?

September 10, 2025Journal Of Computer Networks Architecture and High Performance ComputingOpen Access

Application of Transformer Model and Word Embedding in Sentiment Analisys of Indonesian E-Commerce Application Review

View Full Paper

Ask AI

Bookmark

The application of the transformer model and word embedding methods shows effectiveness in sentiment analysis of Indonesian e-commerce reviews.
The highest accuracy score of 88% was achieved with Word2Vec and FastText, while IndoBERT had an accuracy of 86%.
The study involved extracting review data from the Google Play Store and evaluated models using accuracy, precision, and F1-score.
IndoBERT was found to offer better balance in recall values and F1-scores for recognizing minority class reviews in sentiment analysis.

Authors

KKKadarsih Kadarsih DPDefi PujiantoUniversitas Islam Ogan Komering Ilir

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Analysis compares sentiment recognition in Indonesian e-commerce reviews using transformer model and word embedding techniques, highlighting effectiveness in decision support.

Cite This Study

Kadarsih et al. (2025) studied this question.

synapsesocial.com/papers/68c1b60d54b1d3bfb60eb201 https://doi.org/10.47709/cnahpc.v7i3.6354

View Full Paper

Ask AI

Bookmark

Implication

Analysis compares sentiment recognition in Indonesian e-commerce reviews using transformer model and word embedding techniques, highlighting effectiveness in decision support.

Application of Transformer Model and Word Embedding in Sentiment Analisys of Indonesian E-Commerce Application Review

Key Points

Discussion

Implication

Cite This Study

Application of Transformer Model and Word Embedding in Sentiment Analisys of Indonesian E-Commerce Application Review

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider