Aspect-Based Sentiment Analysis on Application Review using Convolutional Neural Network

Aritonang, Putri Arta; Johan, Monika Evelin; Prasetiawan, Iwan

doi:10.31937/si.v13i1.2684

Cited by 5 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Metode klasifiikasi menggunakan algoritma Convolutional Neural Network (CNN). Hasil penelitian ini skor f1 sebesar 92,23 persen pada klasifikasi aspek dan 95,13 persen pada klasifikasi sentimen, hasilnya menunjukkan bahwa model CNN dapat bekerja dengan sangat baik [20].…”

Section: Pendahuluanunclassified

Analisis Sentimen Pengguna Media Sosial Terhadap Aplikasi M-Health Peduli Lindungi Dengan Metode Lexicon Based Dan Naïve Bayes

Syah,

Hoiriyah,

Walid

2023

IJUBI

View full text Add to dashboard Cite

Pedulilindungi atau satusehat merupakan aplikasi yang dirilis secara resmi guna menangani penyebaran virus Covid-19 dan vaksinasi. Namun, dikarenakan suatu insiden besarnya kebocoran data pribadi, terutama identitas pribadi, kepercayaan masyarakat terhadap aplikasi tersebut sangat rendah. Untuk mengetahui pendapat masyarakat saat ini maka dilakukanlah penelitian dengan mengkombinasikan metode Lexicon Based dan Naïve Bayes. Hasil klasifikasi sentiment memperoleh nilai yaitu 62% negative, 32% netral, 6% positif pada Tiktok. 56% negative, 37% netral, 7% positif pada Youtube. 100% positif pada Twitter, dengan jumlah keseluruhan 118 skor negative, 69 skor netral, 113 skor positif, maka dapat disumpulkan masyarakat memiliki opini negative pada aplikasi peduli lindungi. Hasil evaluasi kinerja model memperoleh akurasi 91%, presisi 94%, recall 82%, f1_scores 86% pada Tiktok, pada Youtube akurasi sebesar 90%, presisi 93%, recall 81%, f1_scores 84%. Pada Twitter akurasi 70%, presisi 23%, recall 33%, f1-scores 28%. Pengkombinasian metode Lexicon Based dan Naïve Bayes ini memiliki akurasi yang sangat tinggi pada media sosial Tiktok dan Youtube, sehingga untuk penelitian selanjutnya pada media sosial Twitter perbanyak data yang diambil. Juga penelitian ini diharapkan dapat membantu membangun kembali aplikasi supaya lebih optimal.

show abstract

Section: Pendahuluanunclassified

Analisis Sentimen Pengguna Media Sosial Terhadap Aplikasi M-Health Peduli Lindungi Dengan Metode Lexicon Based Dan Naïve Bayes

Syah,

Hoiriyah,

Walid

2023

IJUBI

View full text Add to dashboard Cite

show abstract

“…This value can be either positive or negative. This value can be used as a parameter in decision-making [9]- [11]. Sentiment analysis can be performed using several methods such as Random Forest, Support Vector Machine (SVM), and Naïve Bayes [5], [6], [12].…”

Section: Introductionmentioning

confidence: 99%

Sentiment Analysis of Shopee App Reviews Using Random Forest and Support Vector Machine

Suswadi,

Erkamim

2023

Ilk. J. Ilm.

View full text Add to dashboard Cite

During the COVID-19 outbreak, Indonesian marketplaces were significantly impacted including Shopee app. It is necessary to evaluate the features and services of the Shopee application by looking at the feedback given by the public in Google Play Store reviews. This is what prompted research to be conducted from Kaggle data in the form of Shopee reviews. From this data, sentiment analysis is carried out utilizing the Support Vector Machine (SVM) and Random Forest methods. This method are used to classify reviews based on positive and negative sentiments. The results showed that the level of classification accuracy in the Random Forest model is 82.21%. While the SVM model provides a higher level of accuracy of 84.71%. Data exploration on positive and negative sentiment classes is used to find insight into this problem. In positive sentiment, words that often appear such as “belanja”, “aplikasi”, and “barang” are found. As for the negative sentiments, namely “ongkir”, “kirim”, “aplikasi”. These words can be used to be a quality improvement or evaluation for the Shopee company.

show abstract

“…The results of the combination of Naïve Bayes and PSO methods get an accuracy of 93% and AUC of 97.7%. Research [13] used the Convolutional Neural Network (CNN) method for sentiment analysis of PeduliLindungi application user reviews based on aspects of Visual Experience, Scan, Vaccine Certificate, eHac, Covid-19 Test, Login, Performance, and Security. The data used were 2320 instances, and the results of his research obtained an f1 score of 95.13%.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Machine Learning Methods for Classifying User Satisfaction Opinions of the PeduliLindungi Application

Tisna Putra,

Anggrawan,

Hairani

2023

matrik

View full text Add to dashboard Cite

Since the emergence of the Covid-19 virus, the Indonesian government urged people to study, work, and worship or work from home. The social restriction policy has changed people's behavior which requires physical distance in social interaction. The government developed an application to minimize the spread of Covid-19, namely the PeduliLindungi application. The PeduliLindungi application is a tracking application to prevent the spread of Covid-19. The government's policy of implementing the PeduliLindungi application during Covid-19 aroused pros and cons from the public. The volume of PeduliLindungi application review data on Google Play was increasing, so manual analysis could not be done. New analytical approaches needed to be carried out, such as sentiment analysis. This research aimed to analyze user reviews of the PeduilLindungi application using classification methods, namely Support Vector Machine (SVM), Random Forest, and Naïve Bayes. The methods used were Synthetic Minority Oversampling Technique (SMOTE), Random Forest, SVM, and Naïve Bayes. SMOTE was used to balance user review data on the PeduliLindungi application. After the data had been balanced, classification was carried out. The results of this study showed that the Random Forest method with SMOTE got better accuracy than the SVM and Naive Bayes methods, which was 96.3% based on the division of training and testing data using 10-fold cross-validation. Thus, using the SMOTE method could improve the accuracy of classification methods in classifying opinions of user satisfaction with the PeduliLindungi application.

show abstract

Aspect-Based Sentiment Analysis on Application Review using Convolutional Neural Network

Cited by 5 publications

References 9 publications

Analisis Sentimen Pengguna Media Sosial Terhadap Aplikasi M-Health Peduli Lindungi Dengan Metode Lexicon Based Dan Naïve Bayes

Analisis Sentimen Pengguna Media Sosial Terhadap Aplikasi M-Health Peduli Lindungi Dengan Metode Lexicon Based Dan Naïve Bayes

Sentiment Analysis of Shopee App Reviews Using Random Forest and Support Vector Machine

Comparison of Machine Learning Methods for Classifying User Satisfaction Opinions of the PeduliLindungi Application

Contact Info

Product

Resources

About