Implementation of Support Vector Machine Algorithm for Shopee Customer  Sentiment Anlysis

Sitepu, Melda Betaria; Munthe, Ibnu Rasyid; Harahap, Syaiful Zuhri

doi:10.33395/sinkron.v7i2.11408

Cited by 7 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the five sentiment analysis models tested, the mean of the confusion matrix obtained is precision = 1, recall = 0.97, and f1-score = 0.98. From this study, it can be concluded that the SVM algorithm has been proven to apply to performing sentiment analysis on user reviews of Shopee products with an average accuracy rate of 97.3% (Sitepu, Munthe, & Harahap, 2022).…”

Section: Literature Reviewmentioning

confidence: 90%

Sentiment Analysis of Flood Disaster Management in Jakarta on Twitter Using Support Vector Machines

Saddam

Dewantara

Solichin

2023

SinkrOn

View full text Add to dashboard Cite

Floods can cause negative impacts in various aspects, starting from economic, social, to health aspects. Even quoted from the site gis.bnpb.go.id, during 2022, there have been 1031 cases of flood disasters in Indonesia. Meanwhile in Jakarta, in 2022 there have been 14 cases of floods that caused hundreds of people to lose their homes. Several approaches can be taken to determine public opinion about flooding, one of which is text mining with an analysis of community sentiment. Sentiment analysis aims to determine public opinion regarding flood management in the capital city of Jakarta based on positive, neutral, and negative categories. To get the public sentiment, researchers carried out several stages, including the preprocessing stage. After obtaining public sentiment regarding flood management through the preprocessing stage, then classification is carried out based on public opinion so that it can be used by related parties for evaluation material in flood handling. In this study, the classification method used is the SVM method which is one of the supervised learning methods in machine learning. After classification, the next stage is the testing process using the K-Fold Cross Validation method. From the various sentiments obtained from Twitter data, it can be concluded that there are around 414 positive sentiments and 2464 negative sentiments related to flood handling in DKI Jakarta, while the results obtained from the test results show that the accuracy reaches 88.6%, the precision reaches 88.6% and recall reached 89.4%.

show abstract

Section: Literature Reviewmentioning

confidence: 90%

Sentiment Analysis of Flood Disaster Management in Jakarta on Twitter Using Support Vector Machines

Saddam

Dewantara

Solichin

2023

SinkrOn

View full text Add to dashboard Cite

show abstract

“…First component is pre-processing. Pre-processing is a process to remove unnecessary data contained in the text that does not match the required process (Sitepu, et. al., 2022).…”

Section: Methodsmentioning

confidence: 99%

The effect of Chi-Square Feature Selection on Question Classification using Multinomial Naïve Bayes

Yusliani

Aruda

Marieska

et al. 2022

SinkrOn

View full text Add to dashboard Cite

Question classification is one of the essential tasks for question answering system. This task will determine the expected answer type (EAT) of the question given to the system. Multinomial Naïve Bayes algorithm is one of the learning algorithms that can be used to classify questions. At the classification stage, this algorithm used a set of features in the knowledge model. The number of features used can result in curse of dimensionality if the feature is in high dimension. Feature selection can be used to reduce the feature dimension and could increase the system performance. Chi-Square algorithm can be used to select features that describe each category. In this research, the Multinomial Naïve Bayes is used to classify the question sentences and the Chi-Square algorithm is used for the feature selection. The dataset used is a set of Indonesian question sentences, consisting of 519 labeled factoids, 491 labeled non-factoids, and 185 labeled other. The test results showed an increase in accuracy of 0.1 when used feature selection. System accuracy when used feature selection is 0.87 with the number of features used are 248. Without feature selection, the accuracy is 0.77 with the number of features used are 1374.

show abstract

“…Rahat [11] used the same algorithm as Siswanto and reported that SVM provided higher accuracy (82.48%) than NB. Sitepu [12] utilized the SVM algorithm to analyze customer sentiment on Shopee and found that SVM yielded an accuracy rate of 97.3%. Meanwhile, Xu [13] compared the performance of Linear SVM and Naïve Bayes algorithms for text classification, and SVM was found to be superior based on Precision, Recall, F1-score, and Accuracy metrics.…”

Section: Introductionmentioning

confidence: 99%

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

Purbaya¹,

Rakhmadani²,

Arum³

et al. 2023

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

View full text Add to dashboard Cite

Chips are a well-known product among Small and Medium Enterprises (SMEs). In order to enhance the quality of chips as an SME product, sentiment analysis is a crucial step. In this research, sentiment analysis of chip purchases on the Shopee E-marketplace was conducted using the Natural Language Processing (NLP) method, utilizing the N-Gram Model and Term Frequent-Inverse Document Frequency (TF-IDF) as feature extraction techniques, and the Support Vector Machine (SVM) algorithm for sentiment classification. The objective of this research is to identify the most suitable feature extraction model and optimal SVM kernel type from the options of Linear, Polynomial degree, Gaussian RBF, and Sigmoid kernels. Results from the experiments indicate that the TF-IDF and unigram feature extraction techniques offer the best performance for SVM classification when utilizing the Linear kernel. By labeling the dataset, it was observed that using a lexicon-based approach for sentiment classification resulted in 84.31% of the total reviews being positive. The words "price", "cheap" and "quality" in unigram have the highest weights above 0.040. In the unigram model, linear kernel accuracy and precision performance values are 88.4% and 87.3%. At the same time, the recall performance values is 88.4%. The results of the F1-Score assessment matrix from Unigram were 86.9%, Bigram was 78.5% and Trigram was 77.4%. Ultimately, the unigram model combined with a linear kernel in the SVM algorithm demonstrates strong potential for application in the development of various systems focused on detecting user reviews in the Indonesian language on the Shopee E-Marketplace.

show abstract

Implementation of Support Vector Machine Algorithm for Shopee Customer Sentiment Anlysis

Cited by 7 publications

References 18 publications

Sentiment Analysis of Flood Disaster Management in Jakarta on Twitter Using Support Vector Machines

Sentiment Analysis of Flood Disaster Management in Jakarta on Twitter Using Support Vector Machines

The effect of Chi-Square Feature Selection on Question Classification using Multinomial Naïve Bayes

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

Contact Info

Product

Resources

About