Endang Lestari Ruskan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Endang Lestari Ruskan has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Ali Ibrahim
Universitas Sriwijaya
2 shared publications - Dedy Kurniawan
Universitas Sriwijaya, Palembang
2 shared publications - Ali Ibrahim
Universitas Sriwijaya
1 shared publication - Anna Dwi Marjusalinah
Universitas Sriwijaya
1 shared publication - Apriansyah Putra
Universitas Sriwijaya
1 shared publication - Bayu Wijaya Putra
Universitas Sriwijaya
1 shared publication
Latest Publications
- Open Access
- 15 November 2025
- Published by Politeknik Negeri Bengkalis in INOVTEK Polbeng - Seri Informatika
- Vol. 10 (3) , 1623-1633
Comparison of SVM and Naive Bayes Algorithms in Sentiment Analysis of User Reviews on Bukalapak
Indonesia’s rapid e-commerce growth has produced a vast volume of user reviews, yet their use for insight extraction remains limited—particularly for the Bukalapak platform. This study compares the performance of Naïve Bayes and Support Vector Machine for sentiment classification on 10,000 Bukalapak reviews. The workflow includes text preprocessing (cleaning, case folding, tokenization, stopword removal, and stemming) and feature extraction using Term Frequency–Inverse Document Frequency (TF-IDF; max_features = 10,000). Evaluation employs 10-fold cross-validation with accuracy, precision, recall, and F1-score, complemented by a paired t-test for significance. Results show SVM outperforming NB (accuracy 84.48% vs. 83.96%; F1 0.8253 vs. 0.8205) with better consistency (standard deviation ±1.08% vs. ±1.24%). The t-test confirms a significant difference (p = 0.019), with SVM’s advantage most evident for the negative class (precision 0.80 vs. 0.78). Both models underperform on the neutral class due to severe class imbalance. These findings provide empirical evidence for algorithm selection in Indonesian e-commerce sentiment analysis and open avenues for future research using deep learning and class-imbalance handling techniques.
- 15 November 2025
- Published by Politeknik Negeri Bengkalis in INOVTEK Polbeng - Seri Informatika
- Vol. 10 (3) , 1623-1633
Open AccessComparison of SVM and Naive Bayes Algorithms in Sentiment Analysis of User Reviews on Bukalapak
Indonesia’s rapid e-commerce growth has produced a vast volume of user reviews, yet their use for insight extraction remains limited—particularly for the Bukalapak platform. This study compares the performance of Naïve Bayes and Support Vector Machine for sentiment classification on 10,000 Bukalapak reviews. The workflow includes text preprocessing (cleaning, case folding, tokenization, stopword removal, and stemming) and feature extraction using Term Frequency–Inverse Document Frequency (TF-IDF; max_features = 10,000). Evaluation employs 10-fold cross-validation with accuracy, precision, recall, and F1-score, complemented by a paired t-test for significance. Results show SVM outperforming NB (accuracy 84.48% vs. 83.96%; F1 0.8253 vs. 0.8205) with better consistency (standard deviation ±1.08% vs. ±1.24%). The t-test confirms a significant difference (p = 0.019), with SVM’s advantage most evident for the negative class (precision 0.80 vs. 0.78). Both models underperform on the neutral class due to severe class imbalance. These findings provide empirical evidence for algorithm selection in Indonesian e-commerce sentiment analysis and open avenues for future research using deep learning and class-imbalance handling techniques.
- Open Access
- 18 March 2025
- Published by Asosiasi Doktor Sistem Informasi Indonesia in Journal of Information Systems and Informatics
- Vol. 7 (1) , 663-680
Harnessing SVM for Sentiment Analysis: Insights from Gojek's Instagram Engagement
The development of digital technology has changed the transportation industry, including online services such as Gojek. Understanding customer sentiment is key in improving user experience and designing more effective business strategies. This research analyzes Gojek user sentiment on Instagram using Support Vector Machine (SVM). Data is obtained through web scraping, then processed through text cleaning, tokenization, common word removal, and stemming. Features were extracted using Term Frequency-Inverse Document Frequency (TF-IDF) before being classified with SVM. The results showed that the SVM model achieved 70.82% accuracy in classifying user sentiment. Most positive comments highlight the convenience and efficiency of the service, while negative comments are more related to high tariffs, application constraints, and less responsive customer service. These findings provide insights for Gojek to improve marketing strategies, optimize customer service, and adjust fare policies based on user feedback. In addition, this analysis can help in predicting real-time customer satisfaction trends through sentiment monitoring on social media. As a development step, this research recommends further exploration with deep learning and Aspect-Based Sentiment Analysis (ABSA) to improve accuracy and understand the service aspects that have the most influence on customer satisfaction.
- 18 March 2025
- Published by Asosiasi Doktor Sistem Informasi Indonesia in Journal of Information Systems and Informatics
- Vol. 7 (1) , 663-680
Open AccessHarnessing SVM for Sentiment Analysis: Insights from Gojek's Instagram Engagement
The development of digital technology has changed the transportation industry, including online services such as Gojek. Understanding customer sentiment is key in improving user experience and designing more effective business strategies. This research analyzes Gojek user sentiment on Instagram using Support Vector Machine (SVM). Data is obtained through web scraping, then processed through text cleaning, tokenization, common word removal, and stemming. Features were extracted using Term Frequency-Inverse Document Frequency (TF-IDF) before being classified with SVM. The results showed that the SVM model achieved 70.82% accuracy in classifying user sentiment. Most positive comments highlight the convenience and efficiency of the service, while negative comments are more related to high tariffs, application constraints, and less responsive customer service. These findings provide insights for Gojek to improve marketing strategies, optimize customer service, and adjust fare policies based on user feedback. In addition, this analysis can help in predicting real-time customer satisfaction trends through sentiment monitoring on social media. As a development step, this research recommends further exploration with deep learning and Aspect-Based Sentiment Analysis (ABSA) to improve accuracy and understand the service aspects that have the most influence on customer satisfaction.
- Open Access
- 16 January 2025
- Published by Asosiasi Idebahasa Kepri in PUAN INDONESIA
- Vol. 6 (2) , 573-582
Optimalisasi Pembuatan Website Personal bagi Pengajar di Lembaga Pengembangan Dakwah Al-Bahjah Cirebon
Website development usually involves programming experts in creating websites as information media and a server is needed as a home for the website being developed. These two reasons make websites very difficult for laypeople, especially teachers in educational institutions. Teachers have simple duties and functions in teaching. Technically, a teacher must be able to operate applications, both websites and social media information media. On the other hand, a teacher also needs a media for publishing information related to the profession being pursued, not only the publication of personal information, daily activities, but also the publication of teaching materials, new things related to learning, both to students and to the general public. The problem that arises is that not all teachers can create reliable websites and online access. Based on the survey results, at LPD Al Bahjah there are teachers who are very enthusiastic about operating personal websites. The solution offered is in the form of website development on a platform that has a template that is integrated with artificial intelligence in the process of personifying the user interface and selecting a website theme according to user input. The results of the community service carried out are that the community service participants are very enthusiastic in socializing website development, not only general technical use but also successfully creating personal websites.
- 16 January 2025
- Published by Asosiasi Idebahasa Kepri in PUAN INDONESIA
- Vol. 6 (2) , 573-582
Open AccessOptimalisasi Pembuatan Website Personal bagi Pengajar di Lembaga Pengembangan Dakwah Al-Bahjah Cirebon
Website development usually involves programming experts in creating websites as information media and a server is needed as a home for the website being developed. These two reasons make websites very difficult for laypeople, especially teachers in educational institutions. Teachers have simple duties and functions in teaching. Technically, a teacher must be able to operate applications, both websites and social media information media. On the other hand, a teacher also needs a media for publishing information related to the profession being pursued, not only the publication of personal information, daily activities, but also the publication of teaching materials, new things related to learning, both to students and to the general public. The problem that arises is that not all teachers can create reliable websites and online access. Based on the survey results, at LPD Al Bahjah there are teachers who are very enthusiastic about operating personal websites. The solution offered is in the form of website development on a platform that has a template that is integrated with artificial intelligence in the process of personifying the user interface and selecting a website theme according to user input. The results of the community service carried out are that the community service participants are very enthusiastic in socializing website development, not only general technical use but also successfully creating personal websites.
- Open Access
- 30 December 2023
- Published by STMIK Indonesia Padang in The Indonesian Journal of Computer Science
- Vol. 12 (6)
Analisis Pengaruh Strategi Konten Sosial Media Terhadap Aplikasi Layanan Streaming
Social media marketing is becoming a key strategy for streaming applications. This study analyzes the content strategy of the Instagram account @Netflixid and its impact on customer loyalty. The study uses a quantitative approach with an online survey as a data collection method and Structural Equation Modeling (SEM)-Partial Least Squares (PLS) as a research method. The results show that content that reflects the behavior of followers and is animated is preferred by Netflixid audiences. This content strategy also has a positive impact on customer loyalty.
- 30 December 2023
- Published by STMIK Indonesia Padang in The Indonesian Journal of Computer Science
- Vol. 12 (6)
Open AccessAnalisis Pengaruh Strategi Konten Sosial Media Terhadap Aplikasi Layanan Streaming
Social media marketing is becoming a key strategy for streaming applications. This study analyzes the content strategy of the Instagram account @Netflixid and its impact on customer loyalty. The study uses a quantitative approach with an online survey as a data collection method and Structural Equation Modeling (SEM)-Partial Least Squares (PLS) as a research method. The results show that content that reflects the behavior of followers and is animated is preferred by Netflixid audiences. This content strategy also has a positive impact on customer loyalty.
- Open Access
- 30 October 2023
- Published by Institut Teknologi Garut in Jurnal Algoritma
- Vol. 20 (2) , 352-363
Rancang Bangun Aplikasi Sistem Antrian Tamu untuk Mendukung Efektifitas Lahan Parkir Berbasis Online
Kunjungan tamu di berbagai instansi pemerintah adalah sebuah aktivitas yang umum terjadi. Dinas Kesehatan Provinsi Sumatera Selatan juga mengalami hal serupa, dimana kunjungan ini melibatkan berbagai kegiatan seperti pertemuan, audiensi, konsultasi, pelaporan, dan sebagainya. Namun, dengan tingginya frekuensi kunjungan tamu, muncul berbagai tantangan, seperti pegawai tidak bisa menentukan jadwal kunjungan dan tamu yang tidak dapat memprediksi tingkat keramaian sehingga sulit mendapatkan tempat parkir. Beberapa rumah sakit, seperti RSIA Hermina Palembang dan Rumah Sakit Muhammadiyah Palembang, telah menerapkan sistem pengelolaan kunjungan tamu. Sistem-sistem ini fokus pada kemudahan pendaftaran pasien dan administrasi rawat jalan agar tidak mengantri lagi. Namun, perbedaan permasalahan antara Dinas Kesehatan Provinsi Sumatera Selatan dengan RSIA Hermina dan RS Muhammadiyah Palembang adalah fokus pada penjadwalan yang tepat dari pegawai dan menghindari penumpukan lahan parkir bagi para tamu. Metode yang tepat untuk mengatasi masalah ini adalah dengan menerapkan metodologi Rapid Application Development (RAD), yang terdiri dari tiga tahap, yaitu Requirment Planning, Design, dan Implementation. Metode ini melibatkan pengambilan data dan analisis yang meliputi studi literatur, observasi, wawancara, dan pengisian kuisioner sebelum merancang sistem. Dengan menggunakan metodologi ini, akan menghasilkan sebuah sistem yang dapat memberikan informasi tentang jadwal janji temu tamu yang tepat serta menghindari penumpukan lahan parkir dengan membatasi jumlah tamu yang datang pada jam yang sama.
- 30 October 2023
- Published by Institut Teknologi Garut in Jurnal Algoritma
- Vol. 20 (2) , 352-363
Open AccessRancang Bangun Aplikasi Sistem Antrian Tamu untuk Mendukung Efektifitas Lahan Parkir Berbasis Online
Kunjungan tamu di berbagai instansi pemerintah adalah sebuah aktivitas yang umum terjadi. Dinas Kesehatan Provinsi Sumatera Selatan juga mengalami hal serupa, dimana kunjungan ini melibatkan berbagai kegiatan seperti pertemuan, audiensi, konsultasi, pelaporan, dan sebagainya. Namun, dengan tingginya frekuensi kunjungan tamu, muncul berbagai tantangan, seperti pegawai tidak bisa menentukan jadwal kunjungan dan tamu yang tidak dapat memprediksi tingkat keramaian sehingga sulit mendapatkan tempat parkir. Beberapa rumah sakit, seperti RSIA Hermina Palembang dan Rumah Sakit Muhammadiyah Palembang, telah menerapkan sistem pengelolaan kunjungan tamu. Sistem-sistem ini fokus pada kemudahan pendaftaran pasien dan administrasi rawat jalan agar tidak mengantri lagi. Namun, perbedaan permasalahan antara Dinas Kesehatan Provinsi Sumatera Selatan dengan RSIA Hermina dan RS Muhammadiyah Palembang adalah fokus pada penjadwalan yang tepat dari pegawai dan menghindari penumpukan lahan parkir bagi para tamu. Metode yang tepat untuk mengatasi masalah ini adalah dengan menerapkan metodologi Rapid Application Development (RAD), yang terdiri dari tiga tahap, yaitu Requirment Planning, Design, dan Implementation. Metode ini melibatkan pengambilan data dan analisis yang meliputi studi literatur, observasi, wawancara, dan pengisian kuisioner sebelum merancang sistem. Dengan menggunakan metodologi ini, akan menghasilkan sebuah sistem yang dapat memberikan informasi tentang jadwal janji temu tamu yang tepat serta menghindari penumpukan lahan parkir dengan membatasi jumlah tamu yang datang pada jam yang sama.
- Open Access
- 2 October 2023
- Published by Universitas Dharma Andalas in Jurnal Teknologi dan Sistem Informasi Bisnis
- Vol. 5 (4) , 448-453
Analisis Pengaruh Penggunaan Media Sosial Instagram Terhadap Customer Engagement dan Customer Loyalty (Studi Pada Followers Akun Instagram Shopee Food)
The COVID-19 pandemic that hit the world has made many changes in various fields, one of which is technology. This makes the emergence of new technologies that support people's lives. One of them is an online food delivery service application that can help people's lives during a pandemic. Seeing this, one of the Shopee applications has created its Shopee Food feature. To promote and assist users in using Shopee Food, Shopee Food is increasing its CRM activities, especially SCRM (Social Customer Relationship Management), namely implementing CRM activities through social media using the Instagram account @shopeefood_id. Therefore, this research is focused on seeing whether SCRM activities via Instagram @shopeefood_id can affect customer relationships, especially customer engagement and customer loyalty. This study used a quantitative-based survey research method with a sample of 100 respondents. The results of this study state that Social Customer Relationship Management has a positive and significant effect on Customer Engagement, Social Customer Relationship Management has a positive and significant effect on Customer Loyalty, Customer Engagement has a positive and significant effect on Customer Loyalty, and Social Customer Relationship Management has an indirect effect directly to Customer Loyalty through Customer Engagement.
- 2 October 2023
- Published by Universitas Dharma Andalas in Jurnal Teknologi dan Sistem Informasi Bisnis
- Vol. 5 (4) , 448-453
Open AccessAnalisis Pengaruh Penggunaan Media Sosial Instagram Terhadap Customer Engagement dan Customer Loyalty (Studi Pada Followers Akun Instagram Shopee Food)
The COVID-19 pandemic that hit the world has made many changes in various fields, one of which is technology. This makes the emergence of new technologies that support people's lives. One of them is an online food delivery service application that can help people's lives during a pandemic. Seeing this, one of the Shopee applications has created its Shopee Food feature. To promote and assist users in using Shopee Food, Shopee Food is increasing its CRM activities, especially SCRM (Social Customer Relationship Management), namely implementing CRM activities through social media using the Instagram account @shopeefood_id. Therefore, this research is focused on seeing whether SCRM activities via Instagram @shopeefood_id can affect customer relationships, especially customer engagement and customer loyalty. This study used a quantitative-based survey research method with a sample of 100 respondents. The results of this study state that Social Customer Relationship Management has a positive and significant effect on Customer Engagement, Social Customer Relationship Management has a positive and significant effect on Customer Loyalty, Customer Engagement has a positive and significant effect on Customer Loyalty, and Social Customer Relationship Management has an indirect effect directly to Customer Loyalty through Customer Engagement.
- Open Access
- 30 November 2021
- Published by Universitas Budi Darma in The IJICS (International Journal of Informatics and Computer Science)
- Vol. 5 (3) , 266-274
Implementation of Simple Additive Weighting (SAW) Method for Selecting Securities Company
A securities company has a purpose as an intermediary for stock trading between investors and the stock company to be purchased. Securities companies must be listed on the Indonesia Stock Exchange and supervised by the Financial Services Authority. The limited information that potential investors can receive regarding the criteria for selecting securities companies causes potential investors to have difficulty comparing each company. And no system supports decisions in this election. Based on the research, obtained eight assessment criteria in the selection of securities companies, as well as determining the weight of each criterion by calculating the Likert scale and determining the cost or benefit attribute for each criterion, as follows: initial deposit fee (15%) cost, transaction fee (12%) cost, stock recommendation fee (12%) cost, registration process time (12%) cost, support application rating (12%) benefit, company establishment (9%) benefit, customer service response (15%) cost, and features (15%) ) benefits. In this study, the authors use five alternatives. The calculation process results in a ranking, and the top-ranking is a highly recommended alternative based on existing criteria and weights. Then a website-based decision support system is made with the SAW method, which can assist in selecting securities companies based on the desired criteria and weights. Users can also view information on the value of each criterion given by each securities company
- 30 November 2021
- Published by Universitas Budi Darma in The IJICS (International Journal of Informatics and Computer Science)
- Vol. 5 (3) , 266-274
Open AccessImplementation of Simple Additive Weighting (SAW) Method for Selecting Securities Company
A securities company has a purpose as an intermediary for stock trading between investors and the stock company to be purchased. Securities companies must be listed on the Indonesia Stock Exchange and supervised by the Financial Services Authority. The limited information that potential investors can receive regarding the criteria for selecting securities companies causes potential investors to have difficulty comparing each company. And no system supports decisions in this election. Based on the research, obtained eight assessment criteria in the selection of securities companies, as well as determining the weight of each criterion by calculating the Likert scale and determining the cost or benefit attribute for each criterion, as follows: initial deposit fee (15%) cost, transaction fee (12%) cost, stock recommendation fee (12%) cost, registration process time (12%) cost, support application rating (12%) benefit, company establishment (9%) benefit, customer service response (15%) cost, and features (15%) ) benefits. In this study, the authors use five alternatives. The calculation process results in a ranking, and the top-ranking is a highly recommended alternative based on existing criteria and weights. Then a website-based decision support system is made with the SAW method, which can assist in selecting securities companies based on the desired criteria and weights. Users can also view information on the value of each criterion given by each securities company
- Open Access
- 6 May 2020
- Published by Atlantis Press SARL
- p. 207-210
Clustering of Food Security Status in South Sumatera Using Fuzzy C-Means Algorithm
- 6 May 2020
- Published by Atlantis Press SARL
- p. 207-210
Open AccessClustering of Food Security Status in South Sumatera Using Fuzzy C-Means Algorithm
- Open Access
- 6 May 2020
- Published by Atlantis Press SARL
- p. 711-716
Development of Decision Support System for Selection Paskibraka Members of South Sumatera Province Using TOPSIS Method
- 6 May 2020
- Published by Atlantis Press SARL
- p. 711-716
Open AccessDevelopment of Decision Support System for Selection Paskibraka Members of South Sumatera Province Using TOPSIS Method
- Open Access
- 6 May 2020
- Published by Atlantis Press SARL
- p. 696-705
The Determination of Reward and Punishment Using WASPAS Method
- 6 May 2020
- Published by Atlantis Press SARL
- p. 696-705
Open AccessThe Determination of Reward and Punishment Using WASPAS Method