The Accuracy Comparison Between Word2Vec and FastText On Sentiment Analysis of Hotel Reviews
Word embedding vectorization is more efficient than Bag-of-Word in word vector size. Word embedding also overcomes the loss of information related to sentence context, word order, and semantic relationships between words in sentences. Several kinds of Word Embedding are often considered for sentimen...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ikatan Ahli Informatika Indonesia
2022-06-01
|
| Series: | Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) |
| Subjects: | |
| Online Access: | http://jurnal.iaii.or.id/index.php/RESTI/article/view/3711 |
| _version_ | 1797334602318086144 |
|---|---|
| author | Siti Khomsah Rima Dias Ramadhani Sena Wijaya |
| author_facet | Siti Khomsah Rima Dias Ramadhani Sena Wijaya |
| author_sort | Siti Khomsah |
| collection | DOAJ |
| description | Word embedding vectorization is more efficient than Bag-of-Word in word vector size. Word embedding also overcomes the loss of information related to sentence context, word order, and semantic relationships between words in sentences. Several kinds of Word Embedding are often considered for sentiment analysis, such as Word2Vec and FastText. Fast Text works on N-Gram, while Word2Vec is based on the word. This research aims to compare the accuracy of the sentiment analysis model using Word2Vec and FastText. Both models are tested in the sentiment analysis of Indonesian hotel reviews using the dataset from TripAdvisor.Word2Vec and FastText use the Skip-gram model. Both methods use the same parameters: number of features, minimum word count, number of parallel threads, and the context window size. Those vectorizers are combined by ensemble learning: Random Forest, Extra Tree, and AdaBoost. The Decision Tree is used as a baseline for measuring the performance of both models. The results showed that both FastText and Word2Vec well-to-do increase accuracy on Random Forest and Extra Tree. FastText reached higher accuracy than Word2Vec when using Extra Tree and Random Forest as classifiers. FastText leverage accuracy 8% (baseline: Decision Tree 85%), it is proofed by the accuracy of 93%, with 100 estimators. |
| first_indexed | 2024-03-08T08:23:27Z |
| format | Article |
| id | doaj.art-5d0f9a3602674a319e69e358ca275f94 |
| institution | Directory Open Access Journal |
| issn | 2580-0760 |
| language | English |
| last_indexed | 2024-03-08T08:23:27Z |
| publishDate | 2022-06-01 |
| publisher | Ikatan Ahli Informatika Indonesia |
| record_format | Article |
| series | Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) |
| spelling | doaj.art-5d0f9a3602674a319e69e358ca275f942024-02-02T05:13:46ZengIkatan Ahli Informatika IndonesiaJurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)2580-07602022-06-016335235810.29207/resti.v6i3.37113711The Accuracy Comparison Between Word2Vec and FastText On Sentiment Analysis of Hotel ReviewsSiti Khomsah0Rima Dias Ramadhani1Sena Wijaya2Institut Teknologi Telkom PurwokertoTelkom Institute of Technology Purwokerto Institut Teknologi Telkom PurwokertoWord embedding vectorization is more efficient than Bag-of-Word in word vector size. Word embedding also overcomes the loss of information related to sentence context, word order, and semantic relationships between words in sentences. Several kinds of Word Embedding are often considered for sentiment analysis, such as Word2Vec and FastText. Fast Text works on N-Gram, while Word2Vec is based on the word. This research aims to compare the accuracy of the sentiment analysis model using Word2Vec and FastText. Both models are tested in the sentiment analysis of Indonesian hotel reviews using the dataset from TripAdvisor.Word2Vec and FastText use the Skip-gram model. Both methods use the same parameters: number of features, minimum word count, number of parallel threads, and the context window size. Those vectorizers are combined by ensemble learning: Random Forest, Extra Tree, and AdaBoost. The Decision Tree is used as a baseline for measuring the performance of both models. The results showed that both FastText and Word2Vec well-to-do increase accuracy on Random Forest and Extra Tree. FastText reached higher accuracy than Word2Vec when using Extra Tree and Random Forest as classifiers. FastText leverage accuracy 8% (baseline: Decision Tree 85%), it is proofed by the accuracy of 93%, with 100 estimators.http://jurnal.iaii.or.id/index.php/RESTI/article/view/3711word2vec, fast text, sentiment analysis, hotel review |
| spellingShingle | Siti Khomsah Rima Dias Ramadhani Sena Wijaya The Accuracy Comparison Between Word2Vec and FastText On Sentiment Analysis of Hotel Reviews Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) word2vec, fast text, sentiment analysis, hotel review |
| title | The Accuracy Comparison Between Word2Vec and FastText On Sentiment Analysis of Hotel Reviews |
| title_full | The Accuracy Comparison Between Word2Vec and FastText On Sentiment Analysis of Hotel Reviews |
| title_fullStr | The Accuracy Comparison Between Word2Vec and FastText On Sentiment Analysis of Hotel Reviews |
| title_full_unstemmed | The Accuracy Comparison Between Word2Vec and FastText On Sentiment Analysis of Hotel Reviews |
| title_short | The Accuracy Comparison Between Word2Vec and FastText On Sentiment Analysis of Hotel Reviews |
| title_sort | accuracy comparison between word2vec and fasttext on sentiment analysis of hotel reviews |
| topic | word2vec, fast text, sentiment analysis, hotel review |
| url | http://jurnal.iaii.or.id/index.php/RESTI/article/view/3711 |
| work_keys_str_mv | AT sitikhomsah theaccuracycomparisonbetweenword2vecandfasttextonsentimentanalysisofhotelreviews AT rimadiasramadhani theaccuracycomparisonbetweenword2vecandfasttextonsentimentanalysisofhotelreviews AT senawijaya theaccuracycomparisonbetweenword2vecandfasttextonsentimentanalysisofhotelreviews AT sitikhomsah accuracycomparisonbetweenword2vecandfasttextonsentimentanalysisofhotelreviews AT rimadiasramadhani accuracycomparisonbetweenword2vecandfasttextonsentimentanalysisofhotelreviews AT senawijaya accuracycomparisonbetweenword2vecandfasttextonsentimentanalysisofhotelreviews |