Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Jurnal Ilmu Komputer

Analisis Kuantitatif Dampak Endorsement Politik Terhadap Tingkat Elektabilitas Pada Pilkada Serentak 2024 Fristiyanto, Doni; Makhsun
Jurnal Ilmu Komputer Vol 2 No 2 (2024): Jurnal Ilmu Komputer (Edisi Desember 2024)
Publisher : Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

 Simultaneous Regional Head Elections (Pilkada) in Indonesia took place on November 27 2024, covering 545 regions, including 37 provinces, 415 districts and 93 cities. Voter turnout reached an average of 71% nationally, reflecting public enthusiasm for the political process. This research also highlights the phenomenon of political endorsements from national figures which have proven effective in increasing candidate electability. To explore the phenomenon of political endorsement, this research uses Google News as a tool to collect and analyze relevant online news. The results of the analysis show that there is a significant correlation between the candidate's level of popularity and electability level, with a correlation value of 0.757. Apart from that, the level of positive sentiment towards candidate pairs also shows a strong correlation (0.74) with electability, indicating that candidates with high popularity and positive sentiment tend to have better electability. However, this research found that the number of political endorsements had a stronger influence on candidate electability, with a correlation value of 0.758. This shows that political endorsement can be a more significant determining factor in increasing electability compared to just relying on popularity or positive sentiment. This research provides important insights into the role of political endorsements as an effective strategy in increasing voter support for certain candidates.
Analisis Sentimen Pengguna Twitter Terhadap Universitas Pamulang Periode Penerimaan Mahasiswa Gelombang I Tahun Ajaran 2024/2025 Rohmani, Muhammad Faqih; Makhsun
Jurnal Ilmu Komputer Vol 3 No 1 (2025): Jurnal Ilmu Komputer (Edisi Juli 2025)
Publisher : Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The development of information technology has had a significant impact on various aspects of life, including education. One of the universities that has gained public attention is Universitas Pamulang. As one of the largest private higher education institutions in Indonesia, Universitas Pamulang needs to continuously improve. One of the key references for these improvements is public opinion. To understand public opinion regarding Universitas Pamulang, an analysis was conducted on the social media platform Twitter. Therefore, this study examines public sentiment toward Universitas Pamulang using Twitter data and the Naïve Bayes method. The Naïve Bayes method was chosen due to its advantages in text classification, particularly in sentiment analysis. The research data was collected from Twitter during the first wave of new student admissions for the 2024/2025 academic year. The analysis process involved identifying the dominant sentiment (positive, negative, or neutral) in public opinion, exploring the institution's strengths and weaknesses, and providing recommendations for improving the quality of academic services, administration, and the reputation of Universitas Pamulang. The results of this study indicate that the Naïve Bayes algorithm can be effectively used for sentiment analysis, achieving a high level of accuracy. This research is expected to contribute academically to sentiment analysis studies in the higher education sector in Indonesia.
Sentimen Analisis Kesehatan Mental Anxiety dengan Metode Decision Tree Menggunakan Software Orange Eva Fauziah; Makhsun
Jurnal Ilmu Komputer Vol 3 No 1 (2025): Jurnal Ilmu Komputer (Edisi Juli 2025)
Publisher : Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Mental health, particularly anxiety disorders, has become a global concern due to the rising prevalence of mental health issues worldwide. Anxiety significantly affects individuals' quality of life and productivity, making it essential to accurately analyze and detect its symptoms. This study aims to apply the decision tree method for sentiment analysis of anxiety in texts collected from various sources such as mental health forums and social media. The decision tree method was chosen for its simplicity and effectiveness in classifying data based on identified patterns. Orange software was utilized to build the classification model due to its user-friendly interface and visualization capabilities. The results indicate that the decision tree model was able to effectively identify anxiety patterns in the texts, contributing to a better understanding of sentiment analysis in the mental health context. This study also introduces a more accessible approach for practitioners and researchers in this field.