Implementation of n-gram Methodology to Analyze Sentiment Reviews for Indonesian Chips Purchases in Shopee E-Marketplace

Purbaya, Muhammad Eka; Rakhmadani, Diovianto Putra; Arum, Maliana Puspa; Nasifah, Luthfi Zian

doi:10.29207/resti.v7i3.4726

Cited by 5 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The F1-Score assessment matrix for Unigram reached 86.9%, while for Bigram and Trigram it was 78.5% and 77.4% respectively. Overall, the unigram model that uses linear kernels in the SVM algorithm shows significant potential for application in the development of various system focuses (Purbaya et al, 2023).…”

Section: Product Review On Shopeementioning

confidence: 99%

See 1 more Smart Citation

Analysis of TF-IDF and TF-RF Feature Extraction on Product Review Sentiment

Harmandini,

2024

SinkrOn

View full text Add to dashboard Cite

Sentiment analysis of product reviews is critical in understanding customer views and satisfaction, especially in the context of e-commerce applications. A marketplace provides channels where users can submit reviews of the products they purchase. However, due to the large number of reviews in a marketplace, analyzing them is no longer feasible to be performed manually. This research proposes a machine learning implementation to perform sentiment analysis on product reviews. In this research, the product review dataset on Shopee marketplace is used for sentiment analysis by comparing TF-IDF and TF-RF feature extraction using the SVM algorithm with stages of dataset, labeling, feature extraction and accuracy results. The importance of the comparison between TF-IDF and TF-RF feature extraction in this research is related to the need to evaluate and determine which feature extraction method is most effective in increasing the accuracy of sentiment analysis. TF-IDF and TF-RF are two methods commonly used in text analysis, and a comparison of their performance can provide deep insight into the effectiveness of each in the context of product sentiment analysis.Thus, through this comparison, this research aims to determine the best approach that can provide the highest accuracy results, so that the results can serve as a guide for further research. Based on the evaluation, the highest accuracy value is achieved at 92.87% by using TF-IDF and SVM classifiers which outperformed previous research.

show abstract

Section: Product Review On Shopeementioning

confidence: 99%

“…There have been several previous studies, namely sentiment analysis using SVM with an accuracy of 80.90% (Hantoro et al, 2022). Then sentiment analysis using SVM with linear kernel with TF-IDF and unigram extraction features achieved an accuracy of 84.31% (Purbaya et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

Analysis of TF-IDF and TF-RF Feature Extraction on Product Review Sentiment

Harmandini,

2024

SinkrOn

View full text Add to dashboard Cite

show abstract

“…"n" dalam n-gram menunjukkan jumlah item dalam urutan. N-Gram dapat digunakan untuk membantu klasifikasi teks, sebagaimana yang dilakukan oleh [14] dalam mengklasifikasi sentimen terhadap pembelian makanan ringan di Indonesia. [15] Membandingkan penggunaan bi-gram dan penghapusan stopwords pada klasifikasi menggunakan Naïve Bayes.…”

Section: N-gramunclassified

Pemodelan Topik Menggunakan n-Gram dan Non-negative Matrix Factorization

Afidh,

Syahrial

2023

jidt

View full text Add to dashboard Cite

Pemodelan topik merupakan teknik pembelajaran mesin yang digunakan untuk melihat topik dalam sekumpulan dokumen teks. Pada penelitian ini pemodelan topik yang digunakan adalah Non-Negative Matrix Factorization (NMF) dengan n-gram. Preprocessing seperti penghilangan tanda baca, angka dan stopword diimplementasikan pada penelitian ini. Proses ini dilakukan dengan terlebih dahulu mengubah kata yang terdapat dalam artikel menjadi kata berhuruf kecil. Penelitian ini juga mengeksplorasi keefektifan penerapan unigram, bigram, dan trigram pada pemodelan topik. Pada penelitian ini juga menggunakan coherence value untuk menentukan jumlah topik terbaik yang dapat dibentuk. Data yang digunakan pada penelitian ini berjumlah 53.920 artikel berita yang bersumber dari portal berita RMOL.id dan BeritaSatu.com untuk periode Juli sampai Desember 2022. Visualisasi t-SNE digunakan untuk melihat distribusi pembentukan topik. Berdasarkan hasil penelitian yang dilakukan diperoleh bahwa jumlah topik yang dapat dibentuk dari RMOL.id untuk unigram adalah 15 topik dengan nilai coherence value 0.812748, bigram adalah 10 topik dengan nilai coherence value 0.835738 dan trigram adalah 7 topik dengan nilai coherence value 0.830572. Sedangkan pada BeritaSatu.com diperoleh 10 topik untuk unigram dengan nilai coherence value 0.799718, bigram 15 topik dengan nilai coherence value 0.788762 dan trigram 15 topik dengan nilai coherence value 0.801935.

show abstract

“…Changing the composition, which includes capital and lowercase letters, to a uniform form first makes it easier to correct misspelled writing. In table 2, retain consistency in the letter forms; this typically entails changing all of the characters to lowercase [13]. Sometimes writing faults cause a composition that includes capital letters or similar characters to lack coherence [14].…”

Section: Pre-processingmentioning

confidence: 99%

Comparison of Spell Correction in Bahasa Indonesia: Peter Norvig, Lstm, and N-Gram

Kusuma,

Ratnasari

2023

jiko

View full text Add to dashboard Cite

This study conducts a comprehensive comparison of spell-checking methods in Bahasa Indonesia, specifically focusing on three approaches: Peter Norvig's method, Long Short-Term Memory (LSTM), and N-gram. The primary metric for evaluation is the accuracy in correcting spelling errors. Notably, Peter Norvig's method outperforms the others, with N-gram following closely, and LSTM trailing behind. The study draws valuable insights that contribute to the enhancement of spelling correction accuracy in the Bahasa Indonesia language. To carry out the evaluation, the research employs SPECIL data (Spell Error Corpus for Indonesian Language), which includes documents with various error types such as insertion, deletion, transposition, and substitution. The testing dataset consists of 150 words, aligning with the 150-word corpus references from the 'Leipzig Corpora Collection' used for Peter Norvig's and N-gram methods. It's noteworthy that the LSTM method utilizes a reference dataset from SPECIL, comprising 150 data points and specifically focusing on insertion errors for the test data. This research provides valuable insights for researchers, developers, and language technology enthusiasts seeking to refine spell-checking techniques for the Bahasa Indonesia language. By leveraging diverse error types and a standardized testing dataset, the study aims to contribute to the continual improvement of spell-checking tools

show abstract

Implementation of n-gram Methodology to Analyze Sentiment Reviews for Indonesian Chips Purchases in Shopee E-Marketplace

Cited by 5 publications

References 27 publications

Analysis of TF-IDF and TF-RF Feature Extraction on Product Review Sentiment

Analysis of TF-IDF and TF-RF Feature Extraction on Product Review Sentiment

Pemodelan Topik Menggunakan n-Gram dan Non-negative Matrix Factorization

Comparison of Spell Correction in Bahasa Indonesia: Peter Norvig, Lstm, and N-Gram

Contact Info

Product

Resources

About