Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Indonesian Journal of Artificial Intelligence and Data Mining

Sentiment Analysis Motorku X Using Applications Naive Bayes Classifier Method Akhmad Mustolih; Primandani Arsi; Pungkas Subarkah
Indonesian Journal of Artificial Intelligence and Data Mining Vol 6, No 2 (2023): September 2023
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v6i2.24864

Abstract

The rapid development of technology has brought convenience to humans in their daily lives. The continuously evolving technology generates large amounts of data. Data can provide valuable information if processed effectively. The Motorku X application is one of the innovations created by Astra Motor to facilitate consumers or potential customers in servicing and purchasing motorcycles. The Motorku X application generates review data every day. These review data can be utilized for future application development. To make the most of the reviews, sentiment analysis is one of the techniques used to process the review data. Sentiment analysis is a method to measure consumer sentiments in terms of positive or negative reviews. The algorithm used in this research is the Naïve Bayes classifier. One of the advantages of Naïve Bayes is its ability to work quickly and efficiently in terms of computational time. The research consists of several stages: data collection, data labeling, pre-processing, data splitting, tf-idf weighting, implementation of Naïve Bayes classifier, and evaluation of the results. The data comprises 1000 reviews divided into two classes: positive class (number) and negative class (number). The research was conducted with three scenarios of training and testing data sharing: 90%:10%, 80%:20%, and 70%:30%. The best results were achieved with the 90%:10% ratio, with an accuracy of 76%, precision of 76%, and recall of 97%.
Improving K-Means Clustering Accuracy for Academic Success Investigation With Extreme Gradient Boosting Algorithm Irma Darmayanti; Laily Farkhah Adhimah; Rizki Sadewo; Nurul Hidayati; Pungkas Subarkah
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 1 (2024): March 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i1.26657

Abstract

Human Resources (HR) has a very important role in the development of the nation, so to improve the quality of human resources, education is needed. Education has a role in developing science, disseminating, socializing, and applying it. So that education is one of the important factors in advancing a nation. However, there are still many challenges in achieving quality education, especially in developing countries such as Indonesia, such as parental education level, socioeconomic status, and environmental conditions can also affect the quality of education and students' opportunities for academic success. The research methods used in this research are problem identification, data collection, data analysis, and evaluation. The results in this study are an increase in accuracy of 38.55% from the difference in the K-Means accuracy value of 14% resulting from the David Bounded Index and the use of the extreme gradient adaboost algorithm.
Early Prediction of Stroke Disease Diagnosis Patients Using Data Mining Algorithm Comparison Pungkas Subarkah; Wenti Risma Damayanti; Arbangi Puput Sabaniyah
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 1 (2024): March 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i1.25955

Abstract

Stroke constitutes a medical emergency of paramount significance, characterized by a notably elevated mortality rate, and stands as the foremost cause of mortality within hospital settings. The dataset employed for this analysis is sourced from Kaggle, denoted as the Brain Stroke Dataset, encompassing a total of 4981 records. This research aims to carry out early prediction of stroke sufferers using several algorithms including the ANN algorithm, CART, KNN, and the NBC algorithm. The results obtained in the ANN algorithm obtained an accuracy of 93.53%, in the CART algorithm of 95.02%, in the KNN algorithm of 91.09% and in the NBC algorithm of 88.44%. With the outcomes of this research, the use of the cart set of rules may be used for early evaluation of stroke sufferers because it has a good degree of accuracy and is listed inside the excellent type kind