Perbandingan Kinerja Word Embedding Word2vec, Glove, Dan Fasttext Pada Klasifikasi Teks

Nurdin, Arliyanti; Aji, Bernadus Anggo Seno; Bustamin, Anugrayani; Abidin, Zaenal

doi:10.33365/jtk.v14i2.732

Cited by 50 publications

(40 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The rating needs to be converted into positive and negative sentiments. The ratings of "Extraordinary" and "Excellent" were changed to positive labels (1). The ratings of "Average", "Bad", and "Very Bad" are changed to negative labels (-1).…”

Section: Data Annotationmentioning

confidence: 99%

See 1 more Smart Citation

The Accuracy Comparison Between Word2Vec and FastText On Sentiment Analysis of Hotel Reviews

Khomsah¹,

Ramadhani

Wijaya³

2022

J. RESTI (Rekayasa Sist. Teknol. Inf.)

View full text Add to dashboard Cite

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.

show abstract

Section: Data Annotationmentioning

confidence: 99%

“…All vocabulary in the corpus is multiplied by the number of sentences. In the large matrix, most of the value is zero number [1]. This weakness was solved when in 2000, Word embedding was discovered by Mikolov [2].…”

Section: Introductionmentioning

confidence: 99%

The Accuracy Comparison Between Word2Vec and FastText On Sentiment Analysis of Hotel Reviews

Khomsah¹,

Ramadhani

Wijaya³

2022

J. RESTI (Rekayasa Sist. Teknol. Inf.)

View full text Add to dashboard Cite

show abstract

“…Fasttext is a fast and effective method for learning word representations and performing text classification [13]. Fasttext learns words by considering the subwords of the word, then each word will be represented as a set of n-gram characters which allows Fasttext to capture the meaning of shorter words and allows embedding to understand the suffixes and prefixes of words [14]. Because of Fasttext considers subwords, it will be able to capture words that rarely appear in documents and handle the problem of unrecognized words, also known as Out of Vocabulary words (OOV).…”

Section: Fasttextmentioning

confidence: 99%

Aspect Based Sentiment Analysis with FastText Feature Expansion and Support Vector Machine Method on Twitter

Raihan

Setiawan

2022

J. RESTI (Rekayasa Sist. Teknol. Inf.)

View full text Add to dashboard Cite

Social media such as Twitter has now become very close to society. Twitter users can express current issues, their opinions, product reviews, and many other things both positive and negative. Twitter is also used by companies to monitor the assessment of their products among the public as insight that will be used to evaluate what aspects of their products need to be further developed. Twitter with its limitation of only allowing users to post a maximum tweet of 280 characters will make a lot of abbreviated and difficult to understand words used, so it will allow vocabulary mismatch problems to occur. Therefore, in this paper, research conducted on aspect-based sentiment analysis of Telkomsel’s products from the aspects of signal and service by applying feature expansion using Fasttext word embedding to overcome vocabulary mismatch problem and classification with the Support Vector Machine (SVM) method. Sampling technique with Synthetic Minority Oversampling Technique (SMOTE) used to overcome data imbalance. The experimental results show that feature expansion can increase the performance of model. The final results obtained F1-Score value of the model for the signal aspect increased by 27.91% with F1-Score 95.93%, and for the service aspect increased by 42.36% with F1-Score 94.53%.

show abstract

“…Salah satu contoh algoritma rekomendasi yang bisa digunakan yakni Doc2Vec. Doc2vec merupakan pengembangan dari algoritma word2Vec, dimana word2vec menangkap pengertian kata dengan kata yang muncul disekelilingnya [4]. Doc2vec menambahkan konteks didalamnya [5].…”

Section: Pendahuluanunclassified

Implementasi Doc2Vec untuk rekomendasi penginapan di Bali

Purnama

2021

JTIUST

View full text Add to dashboard Cite

Dengan semakin menjamurnya hunian berupa villa di Bali, memberikan pilihan yang beragam bagi para wisatawan yang akan menginap di Bali. Berbagai macam pilihan yang ada seringkali membingungkan wisatawan untuk memilih penginapan sesuai dengan kriteria yang diinginkan. Informasi yang tersedia di internet pun sangat beragam dengan jumlah tak terbatas. Apalagi dengan layanan pemesanan online yang juga banyak bertebaran di internet, wisatawan seringkali harus mengunjungi situs-situs ini satu persatu. Rekomendasi penginapan secara otomatis sangat diperlukan untuk membantu wisatawan dalam mempersempit pilihannya dalam mencari penginapan. Maka pada penelitian ini dibangun sebuah system rekomendasi menggunakan algoritma doc2Vec. Doc2Vec merupakan algoritma pembelajaran tidak terawasi yang akan mengubah dokumen menjadi vektor. Sistem rekomendasi ini dikembangkan menggunakan Bahasa python. Dataset yang digunakan merupakan deskripsi kumpulan villa yang tersebar diseluruh Bali yang berasal dari salah satu agen penyewaaan villa. Dari hasil penelitian yang telah dilaksanakan terbukti algoritma doc2vec memberikan hasil rekomendasi terbaik berdasarkan kueri yang diminta oleh pengguna. Dimana metode PV-DM memberikan hasil yang lebih baik jika dibandingkan metode PV-DBOW dengan tingkat kemiripan rata-rata diatas 60%.

show abstract

Perbandingan Kinerja Word Embedding Word2vec, Glove, Dan Fasttext Pada Klasifikasi Teks

Cited by 50 publications

References 0 publications

The Accuracy Comparison Between Word2Vec and FastText On Sentiment Analysis of Hotel Reviews

The Accuracy Comparison Between Word2Vec and FastText On Sentiment Analysis of Hotel Reviews

Aspect Based Sentiment Analysis with FastText Feature Expansion and Support Vector Machine Method on Twitter

Implementasi Doc2Vec untuk rekomendasi penginapan di Bali

Contact Info

Product

Resources

About