Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : JTH: Journal of Technology and Health

ANALYSIS OF STORE CUSTOMER SENTIMENT USING THE NAIVE BAYES CLASSIFIER METHOD DHENDSUL STORE: (Case Study: Dhedsul Store) Antonius L B Hallan; Gergorius Kopong Pati; Karolus Wulla Rato
JTH: Journal of Technology and Health Vol. 1 No. 2 (2023): October: JTH: Journal of Technology and Health
Publisher : CV. Fahr Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61677/jth.vi.43

Abstract

 Sentiment Analysis is a technique for extracting text data to obtain information about positive, neutral or negative sentiment. Sentiment analysis is provided by internet users on social media to provide a personal assessment or opinion. The Dhedsul shop that often gets user sentiment through social media is the Dhedsul shop. The sentiment of opinions from consumers about the Dhedsul Shop can be analyzed and used to obtain useful information for other customers and the Dhedsul Shop. By using the Text Mining technique, the classification method will determine whether a sentiment is positive, neutral or negative. One algorithm that is widely used in sentiment analysis is the Naïve Bayes classification method. This research uses the Naïve Bayes Classifier (NBC) method with tf-idf weighting accompanied by the addition of an emotional icon (emoticon) conversion feature to determine the existing sentiment classes from tweets about the Dhedsul Store. The research results show that the Naïve Bayes method without adding features is able to classify sentiment with an accuracy value of 80.85%, while if the tf-idf weighting feature is added along with emotional icon conversion it is able to increase the accuracy value to 81%.
VILLAGE POTENTIAL PRIORITIZATION DECISION SUPPORT SYSTEM SAW METHOD Susanti Kaka; Gergorius Kopong Pati; Karolus Wulla Rato
JTH: Journal of Technology and Health Vol. 1 No. 2 (2023): October: JTH: Journal of Technology and Health
Publisher : CV. Fahr Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61677/jth.vi.68

Abstract

Village development is an effort to improve the quality of life and life for the greatest welfare of village communities. Meanwhile, the aim of village development is stated in article 78 paragraph 1, namely improving the welfare of village communities and the quality of human life as well as overcoming poverty through fulfilling basic needs, developing village facilities and infrastructure, developing local economic potential, and using natural resources and the environment in a sustainable manner. As is the case with village development, Watu Wona Village is one with a majority of farmers, which is an example of a road access development plan that really needs assistance from the government in its construction to support the production and sale of agricultural products. Infrastructure is still lacking, damaged infrastructure roads make access to the village difficult. As a result, the flow of goods and services to villages to transport agricultural products is also lacking and hampered. Based on the existing problems, village development planning is needed using a decision support system (SPK) so that village selection in Watu Wona village is faster and more accurate. By using the SAW method comparison
APPLICATION OF THE FP GROWTH ALGORITHM FOR MOBILE PHONE SALES TRANSACTIONS Lende, Marlince; Andreas Ariyanto Rangga; Karolus Wulla Rato
JTH: Journal of Technology and Health Vol. 2 No. 3 (2025): January: JTH: Journal of Technology and Health
Publisher : CV. Fahr Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61677/jth.v2i3.334

Abstract

This study aims to identify consumer purchasing patterns at Bintang Waitabula Mobile Store using data mining techniques, specifically the FP-Growth algorithm. Transactional data were collected through documentation and processed using RapidMiner version 10.1. The FP-Growth method was selected for its efficiency in discovering frequent item combinations without generating candidate sets, unlike the Apriori algorithm. The analysis yielded two association rules with confidence values above 60%, indicating a strong relationship between commonly purchased mobile phone brands such as Samsung and Vivo. The process and results were visualized using diagrams and rule descriptions to support easier interpretation. These findings can serve as the foundation for decision-making in marketing strategies and inventory management. The FP-Growth implementation proved to be efficient and suitable for small to medium-sized retail enterprises.