Article Per Year (5 Year)
p-Index From 2021 - 2026
0.751
P-Index
This Author published in this journals
All Journal JMM (Jurnal Masyarakat Mandiri) Jurnal Teknologi dan Manajemen Industri Terapan Jurnal INFOTEL Jurnal Pustaka Indonesia
Parameswari, Sang Dara
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Other

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Studi Perbandingan Naïve Bayes dan Support Vector Machine (SVM) dalam Analisis Sentimen Pengguna Metaverse Parameswari, Sang Dara; Lubis, Muharman; Suakanto, Sinung; Ramadhan, Yumna Zahran; Amanah, Raisyah Nurul; Dila, Revyolla Ananta
Jurnal Teknologi dan Manajemen Industri Terapan Vol. 4 No. 3 (2025): Jurnal Teknologi dan Manajemen Industri Terapan
Publisher : Yayasan Inovasi Kemajuan Intelektual

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55826/jtmit.v4i3.1122

Abstract

Penelitian ini bertujuan mengevaluasi persepsi publik di Indonesia terhadap isu metaverse melalui analisis sentimen berbasis text mining. Metaverse, yang memadukan media sosial, permainan daring, augmented reality (AR), virtual reality (VR), serta aset digital seperti cryptocurrency, semakin mendapat perhatian sejak pengumuman perubahan nama Facebook menjadi Meta pada tahun 2021 dan memunculkan beragam opini publik. Data diperoleh dari Twitter (X) dan dianalisis menggunakan dua algoritma klasifikasi teks, yaitu Naïve Bayes dan Support Vector Machine (SVM). Dalam penerapannya, Naïve Bayes menggunakan fungsi MultinomialNB, sedangkan SVM dijalankan dengan LinearSVC yang lebih sesuai untuk data teks berdimensi tinggi. Hasil penelitian menunjukkan bahwa SVM memberikan kinerja lebih baik dengan akurasi 78,3% dan Macro-F1 78,3%, dibandingkan Naïve Bayes yang memperoleh akurasi 72,4% dan Macro-F1 sebesar 60,2%. Selain itu, SVM lebih seimbang dalam mengenali seluruh kelas sentimen, khususnya kategori negatif, sementara Naïve Bayes tetap relevan sebagai baseline karena kesederhanaan dan efisiensinya. Penelitian ini berkontribusi dalam menyajikan perbandingan komparatif kedua algoritma pada analisis sentimen metaverse di Indonesia, sekaligus membuka ruang bagi pengembangan metode yang lebih mutakhir pada studi berikutnya.
A Personality-Aware Agentic AI Framework for Academic and Career Recommendation in Higher Education Andalusia, Friska; Suakanto, Sinung; Parameswari, Sang Dara
JPI: Jurnal Pustaka Indonesia Vol. 6 No. 1 (2026): April
Publisher : Yayasan Darussalam Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62159/jpi.v6i1.2084

Abstract

Although personality traits are widely recognized as important predictors of academic success and career preferences, their integration into AI-driven academic advising systems remains limited. Existing approaches predominantly rely on academic performance data and historical learning behavior, often overlooking psychological characteristics that influence students’ decision-making processes. In parallel, recent advances in artificial intelligence have enabled more sophisticated recommendation systems; however, these systems typically lack adaptive reasoning capabilities and do not incorporate personality as a core input variable. This study aims to address these gaps by examining how personality traits can support intelligent academic advising and by proposing a conceptual framework for a personality-aware agentic AI system in higher education. A systematic literature review following PRISMA 2020 guidelines was conducted using the Scopus database. From an initial set of 199 records, 21 studies were selected for qualitative synthesis after applying inclusion and exclusion criteria. The findings reveal three key limitations in existing research (1) personality traits are primarily used as explanatory variables rather than operational components in recommendation systems, (2) AI-based advising systems rely heavily on performance-driven data with limited psychological integration, and (3) there is a lack of unified frameworks that combine psychological modelling with adaptive AI architectures. To address these limitations, this study proposes a novel personality-aware agentic AI framework that integrates personality profiling, agentic AI-based reasoning, and intelligent recommendation mechanisms into a unified architecture. The framework introduces a multi-layered approach consisting of personality modelling, agentic AI processing, and recommendation delivery to support adaptive and context-aware academic and career guidance. This research contributes by bridging the gap between personality psychology and AI-driven recommendation systems while introducing agentic AI as a new paradigm for academic advising. Future research should focus on implementing and empirically validating the proposed framework in real-world higher education environments.
LLM-Based Interview Bot for Student Big Five Assessment and Career Recommendation Parameswari, Sang Dara; Lubis, Muharman; Suakanto, Sinung; Pawlowski, Jan M.
JURNAL INFOTEL Vol 18 No 1 (2026): February
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v18i1.1456

Abstract

The development of Artificial Intelligence (AI) and Natural Language Processing (NLP) offers new opportunities to make psychological assessments more interactive and meaningful. However, personality tests such as the International Personality Item Pool – Big Five Factor Markers (IPIP-BFM-50) still rely on static self-report questionnaires, which may limit engagement and contextual interpretation. This study proposes an InterviewBot-based Big Five Personality system (IB-B5P) that combines rule-based IPIP scoring with Large Language Model (LLM)-driven conversational assessment using GPT-3.5 Turbo. The system generates both quantitative personality scores and qualitative narrative profiles. Evaluation results show moderate to strong correlations (r = 0.31–0.71) between IB-B5P and IPIP scores, with Openness and Extraversion showing statistically significant relationships. These findings suggest that the hybrid rule–LLM approach can approximate IPIP tendencies while providing richer context-aware interpretations. The novelty of this study lies in integrating LLM-based conversational intelligence with a standardized psychometric framework, with potential applications in career guidance, educational counseling, and digital psychological assessment in higher education.
PELATIHAN ELEKTRONIKA DASAR UNTUK MENINGKATKAN LITERASI TEKNOLOGI GURU BERLATAR BELAKANG NON-TEKNIS Pramudita, Brahmantya Aji; Parameswari, Sang Dara; Mariel, Reinald; Akbari, Devan Rizki; Meilikiano, Yoshua; Dewi, Khania Putri Kusuma; Rhomanzah, Donny; Sanjoyo, Danu Dwi; Purnama, Irwan
JMM (Jurnal Masyarakat Mandiri) Vol 10, No 2 (2026): April
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jmm.v10i2.38350

Abstract

Abstrak: Perkembangan teknologi menyebabkan guru membutuhkan pemahaman elektronika untuk meningkatkan literasi teknologi dan minat sains untuk siswa. Akan tetapi, keterbatasan pelatihan untuk guru berlatar belakang non-teknis di tingkat SD/MI masih menjadi hambatan utama. Sehingga, pelatihan literasi teknologi sangat penting untuk meningkatkan kualitas pendidikan. Pelatihan dilakukan dengan mengimplementasikan metode pendekatan partisipatif, kontekstual, dan deksriptif kualitatif. Kemudian, pelatihan dilaksanakan secara sistematis yang diawali dengan identifikasi kebutuhan dan pre-test. Pelaksanaan kegiatan dilakukan dengan memberikan pembekalan teori dan praktik komponen dan alat ukur elektronik kepada peserta pelatihan. Program ini diakhiri dengan post-test dan evaluasi untuk mengukur dan mengetahui keberhasilan peserta dalam mengikuti pelatihan. Hasil post-test menunjukkan pemahama peserta yang baik dengan nilai rata-rata 77,31. Sehingga, hasil pelatihan menunjukkan peningkatan yang signifikan dibandingkan pengetahuan awal peserta yang rendah. Selain itu, hasil dari umpan balik yang diperoleh dari peserta pelatihan bahwa tingkat kepuasan peserta tinggi dengan skor rata-rata 4,2, meskipun peserta masih terdapat kendala dalam memahami materi.Abstract: Technological developments require teachers to understand the fundamentals of electronics for the students to enhance technological literacy and interest in science. However, the lack of training for the non-technical teachers in elementary schools (SD) or Madrasah Ibtidaiyah (MI) is still a main issues. Therefore, technological literacy training is critical for enhancing educational quality. The training was conducted by implementing participatory, contextual, and qualitative descriptive approaches. Then, the training is conducted systematically, starting with an identification of the needs and a pre-test. The program is implemented by providing participants with theoretical and practical briefings on electronic components and measuring tools. The program concludes with a post-test and evaluation to measure and determine the participants' success in the training. The results of training showed that the training effectively improves participants’ understanding of basic electronics and their skills in using measuring instruments. The post-test results showed good participant understanding with an average score of 77.31. Thus, the training results indicate a significant increase compared to the participants' low initial knowledge. Additionally, feedback obtained from the trainees showed a high level of satisfaction with an average score of 4.2, even though some participants still faced obstacles in understanding the material.
Co-Authors Akbari, Devan Rizki Amanah, Raisyah Nurul Andalusia, Friska Brahmantya Aji Pramudita Danu Dwi Sanjoyo Dewi, Khania Putri Kusuma Dila, Revyolla Ananta Irwan Purnama Mariel, Reinald Meilikiano, Yoshua Muharman Lubis Pawlowski, Jan M. Ramadhan, Yumna Zahran Rhomanzah, Donny Sinung Suakanto