Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : SINTECH (Science and Information Technology) Journal

Perbandingan Metode Pembobotan TF-RF Dan TF-ABS Pada Kategorisasi Berita Di BDI Denpasar I Kadek Wahyu Dananjaya; I Gusti Ayu Agung Diatri Indradewi
SINTECH (Science and Information Technology) Journal Vol. 6 No. 1 (2023): SINTECH Journal Edition April 2023
Publisher : Prahasta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31598/sintechjournal.v6i1.1252

Abstract

BDI Denpasar is a government agency tasked with carrying out training and education for human resources of animation, crafts and art. BDI Denpasar in managing news classes in the Kabar Insan Oke service still uses conventional methods. Therefore an automatic news classification module is needed. This study was made to compare the performance level of news classification at BDI Denpasar using K-NN classification with the TF-RF and TF-ABS term weighting methods. Methods that have a high level of performance will be implemented in the news classification module. This research was carried out by collecting news documents, text preprocessing, term weighting, classification, model validation and testing. The K-NN classification uses the n_neighbhor (k), namely k=3, k=5, k=7 and k=9 using a dataset of 324 documents containing 7 classes taken from BDI Denpasar website. Based on the results of the tests performed, TF-RF method obtained a higher performance at k=5 with an accuracy of 71% with a precision of 73% and a recall of 71%. TF-ABS method with the highest performance value is found at k=9 which obtains 70% accuracy, 63% precision and 70% recall. So the method that will be implemented in the news classification module is TF-RF at k=5 with an accuracy of 71% with a precision of 73% and a recall of 71%.
Analisis Sentimen Program Mbkm Pada Media Sosial Twitter Menggunakan KNN Dan SMOTE Komang Pramayasa; I Md Dendi Maysanjaya; I Gusti Ayu Agung Diatri Indradewi
SINTECH (Science and Information Technology) Journal Vol. 6 No. 2 (2023): SINTECH Journal Edition Agustus 2023
Publisher : Prahasta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31598/sintechjournal.v6i2.1372

Abstract

The Merdeka Belajar-Kampus Merdeka (MBKM) program is a relatively new program implemented in Indonesia since February 2020. Like a new program, the implementation of the MBKM program is also followed by various pro and con attitudes. Therefore, a sentiment analysis technique is needed to determine the public opinion towards the MBKM program. The purpose of this study is to determine the performance of the KNN method in performing sentiment classification optimized by the SMOTE method in overcoming the problem of unbalanced data and to determine the tendency of public sentiment towards the implementation of the MBKM program. Based on the research results, the KNN method optimized with the SMOTE method is proven to improve classification performance. From initially producing an accuracy value of 76.13%, precision of 76.03%, recall of 76.13% and f1-score of 76.01% there was an increase in accuracy value to 76.13%, precision to 76.03%, recall to 76.13%, and f1-score to 76.01%. In this study, it was found that community responses tended to be neutral towards the MBKM program. The community feels that the MBKM program is a program that can increase student experience. However, there are still program systems that are considered complicated and need to be evaluated.
Penerapan Metode E-Service Quality Terhadap Pengukuran Tingkat Kepuasan Penggunaan Marketplace Parwita, Wayan Gede Suka; Indradewi, I Gusti Ayu Agung Diatri; Ariantini, Made Suci; Ginantra, Ni Luh Wiwik Sri Rahayu; Putra, I Kadek Andika
SINTECH (Science and Information Technology) Journal Vol. 5 No. 2 (2022): SINTECH Journal Edition Oktober 2022
Publisher : Prahasta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31598/sintechjournal.v5i2.1236

Abstract

Intense competition makes various existing markets must be able to provide the best and satisfaction for users to win the existing competition. In the review of the JD.ID application during versions 6.3 and 6.4 there were several user complaints that led to system and service quality problems. Service quality is one of the factors supporting the success or failure of an information system to provide satisfaction to its users. The purpose of this study was to determine how the influence of electronic service quality (e-service quality) on user satisfaction in the JD.ID application. The type of analysis used in this study is simple regression analysis with descriptive analysis to describe a generalization or explain the research subject based on the dimensions of e-service quality, so that an overview of the effect of e-service quality on user satisfaction can be obtained. The processed data was obtained from distributing questionnaires by using the google form. The results showed that the majority of JD.ID marketplace users in Badung Regency were women. The test results show that e-service quality which consists of dimensions of efficiency, system availability, fulfillment, privacy, responsiveness, compensation, and contact has a significant influence on user satisfaction and has a strong correlation, meaning that the higher the service quality JD has. ID, the higher the level of satisfaction of JD.ID users. It can be said that the service quality of JD.ID is quite good in providing user satisfaction.