Garuda - Garba Rujukan Digital

Improving Panic Disorder Classification Using SMOTE and Random Forest Nurmalasari, Dini; Yuliantoro, Heri R; Qudsi, Dini Hidayatul
Journal of Applied Informatics and Computing Vol. 8 No. 2 (2024): December 2024
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v8i2.8315

Panic disorder is a serious anxiety disorder that can significantly impact an individual's mental health. If left undetected, this disorder can disrupt daily life, social relationships, and overall quality of life. Early detection and intervention are crucial for managing panic disorder and improving the well-being of those affected. Technology plays a pivotal role in facilitating early detection through data-driven approaches that employ algorithms to identify patterns of behavior or symptoms associated with panic disorder. Accurate classification of panic disorder is crucial for effective diagnosis and treatment. However, machine learning models trained on imbalanced datasets, such as those containing panic disorder patients, are prone to overfitting, leading to poor generalization performance. This study investigates the effectiveness of the Synthetic Minority Oversampling Technique (SMOTE) in addressing overfitting in panic disorder dataset classification using the Random Forest algorithm. The results demonstrate that SMOTE significantly improves the classification performance of Random Forest. By mitigating overfitting and improving generalization to unseen data, SMOTE increases accuracy by 15 percentage points. Before using SMOTE, the accuracy was 82%, and after using SMOTE it is 97%. The findings underscore the promise of SMOTE as a tool for boosting the performance of machine learning algorithms in classifying panic disorder from imbalanced data.

Discovering User Sentiment Patterns in Libraries with a Hybrid Machine Learning and Lexicon-Based Approach Nurmalasari, Dini; Qudsi, Dini Hidayatul; Chairani, Nessa; Yuliantoro, Heri R
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 13 No. 3 (2024): NOVEMBER
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v13i3.2217

The need to enhance library services is the focus of this study, which relies on user feedback for data-driven decision-making. Text data from library user surveys conducted at Politeknik Caltex Riau (PCR) is analyzed to categorize sentiment and identify areas for improvement. The biannual student and lecturer feedback collected from 2018 to 2023 through the institution's official survey system (survey.pcr.ac.id) is utilized, providing a comprehensive and robust picture of user needs across five years. Sentiment analysis is employed using the VADER method to classify user comments into positive or negative categories. Text preprocessing techniques, such as stemming, tokenizing, and filtering, are performed to ensure robust classification. Machine learning algorithms – Naïve Bayes, Support Vector Machine (SVM), and Random Forest – are then utilized to evaluate sentiment classification accuracy. The study offers significant findings. Both SVM and Random Forest achieve an outstanding accuracy of 99%, indicating highly reliable sentiment categorization. Notably, these algorithms also achieve 100% precision, recall, and F1-score, demonstrating their effectiveness in accurately identifying positive and negative user sentiment. While Naïve Bayes shows slightly lower accuracy at 98%, it maintains a high recall rate (100%), ensuring all negative feedback is captured. This research presents a novel approach combining user sentiment analysis with a comprehensive five-year dataset. This enables a deeper understanding of evolving user needs and priorities. The high accuracy and effectiveness of the employed algorithms highlight the potential of this methodology for libraries. Libraries can leverage user feedback for evidence-based service improvement and increased user satisfaction.

Discovering User Sentiment Patterns in Libraries with a Hybrid Machine Learning and Lexicon-Based Approach Nurmalasari, Dini; Qudsi, Dini Hidayatul; Chairani, Nessa; Yuliantoro, Heri R
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 13 No. 3 (2024): NOVEMBER
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v13i3.2217

The need to enhance library services is the focus of this study, which relies on user feedback for data-driven decision-making. Text data from library user surveys conducted at Politeknik Caltex Riau (PCR) is analyzed to categorize sentiment and identify areas for improvement. The biannual student and lecturer feedback collected from 2018 to 2023 through the institution's official survey system (survey.pcr.ac.id) is utilized, providing a comprehensive and robust picture of user needs across five years. Sentiment analysis is employed using the VADER method to classify user comments into positive or negative categories. Text preprocessing techniques, such as stemming, tokenizing, and filtering, are performed to ensure robust classification. Machine learning algorithms – Naïve Bayes, Support Vector Machine (SVM), and Random Forest – are then utilized to evaluate sentiment classification accuracy. The study offers significant findings. Both SVM and Random Forest achieve an outstanding accuracy of 99%, indicating highly reliable sentiment categorization. Notably, these algorithms also achieve 100% precision, recall, and F1-score, demonstrating their effectiveness in accurately identifying positive and negative user sentiment. While Naïve Bayes shows slightly lower accuracy at 98%, it maintains a high recall rate (100%), ensuring all negative feedback is captured. This research presents a novel approach combining user sentiment analysis with a comprehensive five-year dataset. This enables a deeper understanding of evolving user needs and priorities. The high accuracy and effectiveness of the employed algorithms highlight the potential of this methodology for libraries. Libraries can leverage user feedback for evidence-based service improvement and increased user satisfaction.

INTEGRASI NAIVE BAYES DAN ITEM-BASED COLLABORATIVE FILTERING DALAM SISTEM PEMETAAN KOMPETENSI MAHASISWA Nurmalasari, Dini; Fadhli, Mardhiah; Yuli Fitrisia, Yuli Fitrisia; Yuliantoro, Heri R
Jurnal Komputer Terapan Vol 11 No 1 (2025): Jurnal Komputer Terapan
Publisher : Politeknik Caltex Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35143/jkt.v11i1.6612

Preparing a strong portfolio is a crucial aspect for students in entering the workforce, one of which can be achieved through participation in various competitions. However, selecting competitions that align with student competencies remains a challenge due to the abundance of competition information, diversity in student interests and abilities, and limitations in budget, time, and resources. This study develops a recommendation system based on a Hybrid Recommendation System designed to map student competencies to relevant competition types. The system integrates the Naive Bayes method to classify student competencies and Item-Based Collaborative Filtering to calculate similarities between competition types based on other users’ preferences. The system is developed incrementally using the waterfall approach, including the stages of planning, analysis, design, implementation, and testing. The model follows standard machine learning workflows, comprising data collection, exploration and preprocessing, model building, performance evaluation, and method integration. The research data includes student profiles, competencies, and competition preferences collected through surveys and internal databases. Evaluation results indicate that the system successfully provides relevant competition recommendations with an accuracy rate of 70%. These results demonstrate the system’s contribution in assisting students to select competitions that match their competencies, presented in a user-friendly web-based application.

Analisis Faktor-Faktor Yang Mempengaruhi Minat Mahasiswa Dalam Pemilihan Karir Menjadi Auditor (Studi Empiris Pada Mahasiswa Akuntansi Perpajakan Politeknik Caltex Riau) Yuliantoro, Heri R; Nurmalasari, Dini; Putri Radha
Jurnal Ilmiah Raflesia Akuntansi Vol 11 No 2 (2025): Jurnal Ilmiah Raflesia Akuntansi
Publisher : Politeknik Raflesia Press

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

The purpose of this study is to ascertain how accounting students' interest in a career as auditors is influenced by societal values, the workplace, financial incentives, job market factors, and personality. The subjects of this study are Caltex Riau Polytechnic students enrolled in the tax accounting study program. 201 Caltex Riau Polytechnic tax accounting study program students made up the research's population. This study's sample consisted of 66 students from tax accounting education programs in their 20th and 21st generations. By using Likert scale-based surveys to gather data, this study employs quantitative approaches. Primary data was employed as the data source for this study. Descriptive statistical analysis, data quality testing, traditional assumption testing, and hypothesis testing are the data analysis methods employed in this study. SPSS 23 is the media or analytical tool utilized in this study. According to the study's findings, the factors of social values, the workplace culture, and financial incentives significantly and negatively affect accounting students' interest in pursuing a career as auditors, whereas personality traits and job market considerations significantly and favorably influence this interest.

Title

Found 5 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 5 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 5 Documents
Search