Claim Missing Document
Check
Articles

Found 29 Documents
Search

Application of Sentiment Analysis as an Innovative Approach to Policy Making: A review Firdaus, Asno Azzawagama; Saputro, Joko Slamet; Anwar, Miftahul; Adriyanto, Feri; Maghfiroh, Hari; Ma'arif, Alfian; Syuhada, Fahmi; Hidayat, Rahmad
Journal of Robotics and Control (JRC) Vol. 5 No. 6 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i6.22573

Abstract

This literature review comprehensively explains the role of sentiment analysis as a policymaking solution in companies, organizations, and individuals. The issue at hand is how sentiment analysis can be effectively applied in decision making. The solution is to integrate sentiment analysis with the latest NLP trends. The contribution of this research is the assessment of 100-200 recent studies in the period 2020-2024 with a sample of more than 5,000 data, as well as the impact of the resulting policy recommendations. The methods used include evaluation of techniques such as Deep Learning, lexicon-based, and Machine Learning, using evaluation matrices such as F1-score, precision, recall, and accuracy. The results showed that Deep Learning techniques achieved an average accuracy of 93.04%, followed by lexicon-based approaches with 88.3% accuracy and Machine Learning with 83.58% accuracy. The findings also highlight the importance of data privacy and algorithmic bias in supporting more responsive and data-driven policymaking. In conclusion, sentiment analysis is reliable in areas such as e-commerce, healthcare, education, and social media for policy-making recommendations. However, special attention should be paid to challenges such as language differences, data bias, and context ambiguity which can be addressed with models such as mBERT, model auditing, and proper tokenization.
Sentiment Analysis on Marketplace in Indonesia using Support Vector Machine and Naïve Bayes Method Muhammad Mujahid Dakwah; Asno Azzawagama Firdaus; Furizal Furizal; Rangga Faresta
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 10 No. 1 (2024): March
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v10i1.28070

Abstract

This research addresses the challenges of marketplace customer feedback, which is an important aspect in today's era of online transactions. Marketplaces often receive many unsatisfactory comments from their customers through social media platforms. One approach that can be used to address this is sentiment analysis. This research contributes new insights as recommendations for marketplaces based on customer opinions on available services and delivery. The sentiment analysis methods used are Naive Bayes and Support Vector Machine because they are considered the best methods in training text-based classification models. Before being classified, the data goes through preprocessing stages such as cleaning, case folding, filtering, stemming, and tokenizing, as well as feature extraction stages using Term Frequency - Inverse Document Frequency (TF-IDF). The objects analyzed are divided into several well-known marketplaces in Indonesia such as Tokopedia, Lazada, and Shopee in discussing services and delivery of goods. The data used in this study comes from Twitter (X) social media accessed on August 27, 2023, using crawling techniques and successfully obtained as much as 2057 Tweet data. The best accuracy is obtained in the SVM method when compared to the Naive Bayes method. Words obtained based on service talks include price, service, application service, feedback, independence, and others. As for the delivery of goods, common words such as COD, delivery, package, courier, cheap, price, and others appear. Both methods used have good accuracy and can be recommended for use in similar research.
Prediction of Presidential Election Results using Sentiment Analysis with Pre and Post Candidate Registration Data Asno Azzawagama Firdaus; Anton Yudhana; Imam Riadi
Khazanah Informatika : Jurnal Ilmu Komputer dan Informatika Vol. 10 No. 1 (2024): April 2024
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v10i1.4836

Abstract

Social-media is a solution for politicians as a campaign tool because it can save costs compared to conventional campaigns. The 2024 Indonesian presidential election has attracted public attention, especially among social media users. Twitter, as one of the most widely used social media platforms in Indonesia, has become an effective campaign platform. Sentiment analysis is one approach that can be used to measure public opinion on Indonesian presidential candidates based on Twitter data. The data was collected before the declaration of candidates in March 2023 and shortly after the registration of presidential and vice-presidential candidates in November 2023. The data obtained amounted to 15,000 in March 2023 collection and 11,569 in November 2023 collection and used manual labeling by linguists. After removing duplicated tweets, the data changed to 10,569 data with each candidate having 3,523 data for March 2023 and 4,893 data, with each candidate pair having 1,631 data for November 2023. The sentiment analysis classification model is determined using the Naïve Bayes and Support Vector Machine (SVM) methods with Term Frequency-Inverse Document Frequency (TF-IDF) feature extraction. Based on the data, the highest percentage of positive sentiment for the data obtained in March 2023 is for Ganjar Pranowo data by 77.94% and the highest percentage of negative sentiment is for Anies Baswedan data by 31.39%. Meanwhile, for the data obtained in November 2023, the highest positive sentiment was obtained for the candidate pair Ganjar Pranowo - Mahfud MD by 69.16%, and the highest negative sentiment was found in the data Prabowo Subianto - Gibran Rakabuming Raka by 52.12%. Words that frequently appeared in the positive sentiment for Ganjar Pranowo - Mahfud MD included "strong", "corruption", "support", "appreciation", and others. This research achieved the highest accuracy for SVM method which is 86% and Naive Bayes method which is 79%.
ANALISIS EFISIENSI APBN ERA PRABOWO: KAJIAN EKONOMI DAN ANALISIS SENTIMEN PUBLIK Pramesti, Retta Farah; Firdaus, Asno Azzawagama; Yulita, Khairanis; Thoyyibah, Mazraatin
Jesya (Jurnal Ekonomi dan Ekonomi Syariah) Vol 8 No 2 (2025): Artikel Riset Juli 2025
Publisher : LPPM Sekolah Tinggi Ilmu Ekonomi Al-Washliyah Sibolga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36778/jesya.v8i2.2054

Abstract

Studi ini mengevaluasi efisiensi anggaran dalam Anggaran Pendapatan dan Belanja Negara (APBN) 2025, khususnya penghematan Rp306,69 triliun yang dialokasikan untuk mendanai program Makanan Bergizi Gratis (MBG) di bawah pemerintahan Presiden Prabowo Subianto. Pendekatan metode campuran digunakan, menggabungkan analisis kuantitatif (korelasi Pearson dan K-Means Clustering pada data anggaran dan efisiensi dari 78 kementerian/lembaga) dengan analisis sentimen kualitatif-komputasional dari media sosial X (Twitter) menggunakan algoritma Naïve Bayes. Hasil menunjukkan korelasi yang sangat kuat (r = 0,957) antara ukuran anggaran dan efisiensi, tetapi hanya 7 kementerian yang masuk dalam klaster efisiensi tinggi. Analisis sentimen mengungkapkan persepsi publik yang dominan positif terhadap kebijakan MBG, meskipun bias model hadir karena ketidakseimbangan data. Studi ini merekomendasikan lima strategi utama: memperkuat penganggaran berbasis kinerja, memantau program MBG, mengoptimalkan teknologi manajemen anggaran, mendorong partisipasi publik, dan mendiversifikasi pembiayaan inovatif. Secara keseluruhan, temuan tersebut menyoroti pentingnya tata kelola fiskal yang tidak hanya efisien tetapi juga adaptif dan inklusif untuk mendukung pembangunan berkelanjutan.
PELATIHAN DESAIN GRAFIS SEBAGAI UPAYA PENINGKATAN PENGETAHUAN DAN KETERAMPILAN DALAM PEMASARAN KONTEN SEBAGAI PELUANG MENDAPATKAN PASSIVE INCOME BAGI KARANG TARUNA CIPTA RASA DAYA DI DESA KARANG SIDEMEN Syuhada, Fahmi; Saputra, Joni; Adipta, Marazaenal; Anggarista, Randa; Kumoro, Danang Tejo; Afriansyah, M.; Lonang, Syahrani; Putra, Ahmad Fatoni Dwi; Firdaus, Asno Azzawagama; Pratama, Ramadhana Agung; Yamin, Muhamad
Jurnal Abdi Insani Vol 12 No 5 (2025): Jurnal Abdi Insani
Publisher : Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/abdiinsani.v12i5.2235

Abstract

The Community Partnership Empowerment activity aimed to enhance the skills and knowledge of the youth in Karang Sidemen Village, Central Lombok, in the field of digital creative economy, specifically through digital content marketing that can generate passive income. The PKM program is supported by the Directorate of Research, Technology, and Community Service through the BIMA 2024 program. The activities included a socialization session on the concept of the creative economy and technical training on using Adobe Illustrator, where participants were encouraged to market their creations on platforms like Shutterstock. The outcomes of this program showed an improvement in participants' graphic design skills, as evidenced by their ability to create logos, set up Shutterstock accounts, and independently upload their work. Additionally, this activity involved students under the Merdeka Belajar-Kampus Merdeka (MBKM) scheme, providing them with experiential learning outside the campus. In conclusion, this program successfully made a positive impact on digital literacy and the creative economy in the community and is expected to contribute to the village's economic sustainability through the empowerment of local potential in a sustainable manner.
Model Deteksi Jumlah Kendaraan Bermotor Menggunakan Algoritma You Only Look Once (Yolo) V4 Di Parkiran Universitas Qamarul Huda Badaruddin Bagu Ega Silpia Aulia; Syuhada, Fahmi Syuhada; Asno Azzawagama Firdaus
SainsTech Innovation Journal Vol. 7 No. 2 (2024): SIJ VOLUME 7 NOMOR 2 TAHUN 2024
Publisher : LPPM Universitas Qamarul Huda Badaruddin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37824/sij.v7i2.2024.756

Abstract

Kemajuan teknologi yang pesat telah mendorong berbagai inovasi dalam sistem berbasis Internet of Things (IoT), termasuk pada konsep smart city. Salah satu tantangan di era ini adalah manajemen parkir, terutama dalam mendeteksi keberadaan kendaraan bermotor. Keterbatasan ruang parkir di lingkungan pendidikan, seperti Universitas Qomarul Huda Badaruddin Bagu, sering kali menjadi penyebab kemacetan. Sistem parkir konvensional yang diawasi oleh petugas sering kali tidak efisien dan tidak menyediakan informasi real-time mengenai ketersediaan tempat parkir. Penelitian ini bertujuan untuk mengembangkan model deteksi kendaraan bermotor di area parkir Universitas Qomarul Huda Badaruddin Bagu menggunakan metode YOLO (You Only Look Once) V4. Data yang digunakan berupa gambar parkiran yang diambil dari kamera CCTV di area parkir kampus. Model YOLO diimplementasikan untuk mendeteksi kendaraan, khususnya motor, dan hasil deteksinya dibandingkan dengan perhitungan manual untuk mengevaluasi akurasinya. Program yang dihasilkan diharapkan mampu memberikan solusi yang lebih efektif dalam memantau kapasitas parkir dan memudahkan pengelolaan fasilitas parkir di kampus.
The Role of Sentiment Analysis in Election Predictions Compared to Electability Surveys Firdaus, Asno Azzawagama; Faresta, Rangga Alif; Yunus, Muhajir
Indonesian Journal of Modern Science and Technology Vol. 1 No. 1 (2025): January
Publisher : CV. Abhinaya Indo Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64021/ijmst.1.1.1-8.2025

Abstract

Indonesia has just held the voting process for the Presidential Election. This has become a discussion of various media to social media, especially Twitter. However, when making predictions based on social media it will be so difficult if there is no specific technique or method for handling it. The prediction method we found in Indonesia often uses electability surveys in elections, but this research will compare it with sentiment analysis that utilizes social media in data collection. Another novelty is the data used during candidate campaign debates using the Support Vector Machine (SVM) method in class classification. The results obtained show that there are still differences between electability and sentiment, but this is due to several factors such as the amount of data, data objects, data collection time span, and methods. Overall, the SVM method has an accuracy of more than 0.75 on all three candidate datasets, proving that this method can be applied to similar cases.
Classification of Stunting in Toddlers using Naive Bayes Method and Decision Tree Maulana, Adrian; Ilham, Muhammad; Lonang, Syahrani; Insyroh, Nazaruddin; Sherly da Costa, Apolonia Diana; B. Talirongan, Florence Jean; Furizal, Furizal; Firdaus, Asno Azzawagama
Indonesian Journal of Modern Science and Technology Vol. 1 No. 1 (2025): January
Publisher : CV. Abhinaya Indo Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64021/ijmst.1.1.28-33.2025

Abstract

Child stunting is a health problem that has a major impact on their physical growth and brain development. This study aims to create a model that can predict the risk of stunting using machine learning technology, in order to provide assistance quickly. Using data from 7,573 children, which included information such as age, weight, height gender and breastfeeding status, we tried two methods, Naive Bayes and Decision Tree. As a result, Naive Bayes was more accurate and the success rate reached 92%, compared to Decision tree which was only 88%. With this model, it is hoped that health workers will find it easier to find children at risk of stunting, so that preventive action can be taken earlier. This research aims to provide technology-based solutions to overcome the problem of stunting in the community.
Data Analysis of Student Monitoring Using the K-Means Clustering Method Sulistiani; Habibi , Ahmad Rizky Nusantara; Maulana , Adrian; Talirongan , Hidear; Abao , Anrom G.; Elmalky , Ahmed Mahmoud Zaki; Firdaus, Asno Azzawagama
Indonesian Journal of Modern Science and Technology Vol. 1 No. 2 (2025): May
Publisher : CV. Abhinaya Indo Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64021/ijmst.1.2.50-57.2025

Abstract

This study aims to group student monitoring data by focusing on two main variables, namely anxiety level and mood score, using the K-Means Clustering method. The research data was obtained from the Kaggle platform, which contains 1000 rows of data with nine attributes, including Student ID, Date, Class Time, Attendance Status, Stress Level, Sleep Hours, Anxiety Level, Mood Score, and Risk Level. The research process involved several stages, from problem identification, data collection, data cleaning and preprocessing, to the application of the K-Means algorithm. The analysis results showed that the data could be divided into two main groups: Cluster 1 consists of students with low to moderate anxiety levels and high mood scores, while Cluster 2 includes students with high anxiety and low mood scores. These findings provide relevant information for schools or campuses to design more effective psychological support and emotional monitoring programs. Additionally, this clustering method can serve as a foundation for developing an early detection system for psychological issues among students.
Sentiment Analysis of User Reviews of TikTok App on Google Play Store Using Naïve Bayes Algorithm Hasanah, Rakyatol; Sani SR, Sahrul; Munzir, Misbahul; Firdaus, Asno Azzawagama; Sulton, Chaerus; Yunus, Muhajir
Indonesian Journal of Modern Science and Technology Vol. 1 No. 2 (2025): May
Publisher : CV. Abhinaya Indo Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64021/ijmst.1.2.58-64.2025

Abstract

In recent years, user interaction through mobile applications has grown rapidly, making user reviews an important source of feedback for improving service quality. This study explores sentiment analysis on 5,000 user reviews of the TikTok application, collected from the Google Play Store using the google-play-scraper library. The data underwent several preprocessing steps, such as case folding, text cleaning, and selecting relevant columns like review content and rating score. Sentiment labeling was based on rating values: scores of 4 and 5 were treated as positive, while scores of 1 and 2 were considered negative. From the results, it was observed that negative reviews appeared more frequently, indicating an imbalance in the dataset. Despite this, the Naïve Bayes classification algorithm still achieved a reasonably good performance in categorizing the sentiments. These findings suggest that even with simple models, valuable insights can be gained from user-generated content. Moreover, the results provide meaningful input for TikTok developers to better understand user concerns and emphasize the potential need for applying balancing techniques in future analysis. Further studies are encouraged to explore other algorithms that may improve sentiment classification accuracy on more complex datasets.