Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Jurnal Edukasi dan Penelitian Informatika (JEPIN) Tech-E JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING
Alqis Rausanfita
Unknown Affiliation
Computer Science & IT Education Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Analisis sentiment komentar Instagram bakal calon presiden menggunakan metode Support Vector Machine Alqis Rausanfita; Ramadan, Arip; Dzulfikar Fauzi, Muhammad; Mafidah, Qori Emalia Putri; Ramona, Emilia; Mahardika Putra, Yudha
Tech-E Vol. 7 No. 1 (2023): TECH-E (Technology Electronic)
Publisher : Fakultas Sains dan Teknologi-Universitas Buddhi Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31253/te.v7i1.2289

Abstract

The rising number of Instagram user affecting higher number of comments appear on post especially Instagram accounts of Indonesia's 2024 presidential candidates that made it difficult to understand the public sentiment towards presidential candidate. Therefore, this research aims to classify Indonesian sentiment on Instagram comments of 2024 Indonesian presidential candidates using the Support Vector Machine method. The classified sentiment is divided into three classes, namely positive, negative, and neutral. The results shows that Sentiment Analysis of Comments on Instagram Posts of Indonesia's 2024 Presidential Candidates Using The Support Vector Machine Method has a good accuracy value of 89.41%. This results also obtain recall and precision values of 89% and 87% respectively.
Content-Based Book Recommendation System Using TF-IDF and Cosine Similarity Gede Satyamahinsa Prastita Uttama; Dharma Wiguna Limmarga; Gerrard Sebastian; Alqis Rausanfita
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 10 No. 1 (2026): Issues July 2026
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v10i1.17131

Abstract

The growth of digital platforms offering a wide variety of content or products often leads to information overload, making it difficult for users to find items that match their preferences. This research aims to design and implement a content-based recommendation system capable of providing personalized recommendations based on the similarity of item characteristics. The methods employed include data pre-processing (case folding and text cleaning), text representation using Term Frequency–Inverse Document Frequency (TF-IDF), and the measurement of similarity between objects using Cosine Similarity. The dataset contains 133,102 book titles, with descriptive attributes converted into numerical vectors to form the basis of the recommendation process. The quality of the recommendations was evaluated using two complementary approaches: intrinsic metrics (average Cosine Similarity and Average Intra-List Similarity) and user-based validation via a questionnaire completed by 31 respondents who assessed 20 sample books, measured using Precision@5, Recall@5 and F1@5 under a leave-one-out protocol. The research results show that the system generates recommendations that are relevant to the reference objects and are confirmed by the preferences of real users. This approach is effective when applied in situations where there is limited user interaction data (cold-start).
Studi Komparasi Metode Klasik dan IndoBERT untuk Analisis Sentimen Berbasis Aspek Pelaku Program MBG di Platform X Alqis Rausanfita; Affifah Mutiara Pertiwi; Vessa Rizky Oktavia
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol. 12 No. 2 (2026): Volume 12 No 2
Publisher : Program Studi Informatika

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

Abstract

Program Makan Bergizi Gratis (MBG) memunculkan beragam respons publik, khususnya terkait kredibilitas dan kinerja pelaku pelaksanaannya. Media sosial X menjadi ruang bagi masyarakat untuk menyampaikan dukungan, kritik, maupun pandangan terhadap pelaksanaan program secara real-time. Penelitian ini bertujuan mengklasifikasikan sentimen publik terhadap aspek pelaku Program MBG serta membandingkan kinerja metode klasifikasi klasik dengan model berbasis Transformer. Data diperoleh melalui scraping platform X menggunakan kata kunci “MBG” dan “Makan Bergizi Gratis” pada periode Januari 2025 hingga April 2026. Sebanyak 795 tweet dikumpulkan dan diperoleh 789 data setelah penghapusan duplikasi, kemudian diklasifikasikan menjadi sentimen positif, negatif, dan netral. Metode yang dibandingkan meliputi Naive Bayes, SVM, KNN, Random Forest, dan IndoBERT, dengan Random Oversampling untuk menyeimbangkan data. IndoBERT memberikan kinerja terbaik dengan akurasi 83,54%, presisi 80,43%, recall 78,41%, dan F1-score 79,28%. Hasil tersebut menunjukkan bahwa representasi bahasa berbasis konteks melalui IndoBERT mampu meningkatkan kinerja klasifikasi sentimen dibandingkan metode klasik. Penelitian ini memberikan gambaran empiris respons publik terhadap aspek pelaku Program MBG serta kontribusi metodologis dengan perbandingan lima pendekatan klasifikasi.
Co-Authors Affifah Mutiara Pertiwi Arip Ramadan Dharma Wiguna Limmarga Dzulfikar Fauzi, Muhammad Gede Satyamahinsa Prastita Uttama Gerrard Sebastian Mafidah, Qori Emalia Putri Mahardika Putra, Yudha Ramona, Emilia Vessa Rizky Oktavia