Article Per Year (5 Year)
p-Index From 2021 - 2026
4.379
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) ComEngApp : Computer Engineering and Applications Journal Jurnal Ilmu Komputer dan Informasi Jupiter Bulletin of Electrical Engineering and Informatics Scientific Journal of Informatics ICON-CSE Annual Research Seminar PROCEEDING IC-ITECHS 2014 Sinkron : Jurnal dan Penelitian Teknik Informatika Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) JPPPF (Jurnal Penelitian dan Pengembangan Pendidikan Fisika) Dinamisia: Jurnal Pengabdian Kepada Masyarakat Jurnal Inovasi Hasil Pengabdian Masyarakat (JIPEMAS) Jurnal Linguistik Komputasional Sriwijaya Journal of Informatics and Applications Jurnal Generic JITSI : Jurnal Ilmiah Teknologi Sistem Informasi Jurnal Pengabdian Kolaborasi dan Inovasi IPTEKS Jurnal Pendidikan IPA Indonesia
Novi Yusliani
Department Informatics Engineering, Faculty Of Computer Science, Sriwijaya University
Agriculture, Biological Sciences & Forestry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Library & Information Science Physics Social Sciences Other

Published : 43 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 43 Documents
Search

 1   2   3   4   5 
Sistem Rekomendasi Artikel Ilmiah Berbasis Web Menggunakan Content-based Learning dan Collaborative Filtering Betharia Sri Fitrianti; Muhammad Fachurrozi; Novi Yusliani
Generic Vol 10 No 1 (2018): Vol 10, No 1 (2018)
Publisher : Fakultas Ilmu Komputer, Universitas Sriwijaya

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

Abstract

Penelitian ini mengimplementasikan metode content-based learning dan collaborative filtering pada sistem rekomendasi artikel ilmiah berbasis web untuk merekomendasikan artikel ilmiah berbahasa Inggris. Sistem memiliki empat komponen, yaitu analisa konten, profile learner, komponen penyaringan, dan pengambilan dokumen. Content-based learning diimplementasikan pada komponen analisa konten yang bertugas mengidentifikasi masukan berupa artikel ilmiah berbahasa Inggris. Profile learner dilakukan untuk menghitung kemiripan antar pengguna setelah sistem mendapatkan feedback berupa rating dari pengguna. Collaborative filtering diimplementasikan pada komponen penyaringan yang bertugas untuk merekomendasikan artikel kepada pengguna setelah sistem mendapatkan hasil kemiripan antar pengguna. Pengambilan dokumen dilakukan pada proses pengambilan artikel yang dicari oleh pengguna. Uji coba dilakukan pada 100 artikel ilmiah, 6 kelas kategori, serta melibatkan 35 pengguna. Hasil penelitian ini membuktikan bahwa implementasi metode content-based learning dan collaborative filtering pada sistem rekomendasi artikel ilmiah berbasis web mampu memberikan tingkat relevansi dan efektifitas sebesar 0.801 berdasarkan Mean Average Precision dan 0,851 berdasarkan Mean Absolute Error.
Pemodelan Topik Menggunakan Metode Latent Dirichlet Allocation dan Gibbs Sampling Rizki Ramadandi; Novi Yusliani; Osvari Arsalan; Rizki Kurniati; Rahmat Fadli Isnanto
Generic Vol 14 No 2 (2022): Vol 14, No 2 (2022)
Publisher : Fakultas Ilmu Komputer, Universitas Sriwijaya

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

Abstract

Pemodelan topik adalah suatu alat yang digunakan untuk menemukan topik laten pada sekelompok dokumen. Pada penelitian ini dilakukan pemodelan topik dengan menggunakan metode Latent Dirichlet Allocation dan Gibbs Sampling. Enam artikel berita Bahasa Indonesia telah dikumpulkan dari portal berita detiknews dengan menggunakan metode Web Scrapper. Artikel berita dibagi menjadi dua kategori utama yaitu, narkoba dan COVID-19. Analisis model LDA dilakukan dengan menggunakan metode koherensi topik pengukuran skor UCI dengan hasil penelitian menyebutkan diperoleh lima buah topik optimal pada kedua konfigurasi pengujian.
Klasifikasi Pertanyaan Berbahasa Indonesia Menggunakan Algoritma Support Vector Machine dan Seleksi Fitur Mutual Information syechky al qodrin aruda; Novi Yusliani; Alvi Syahrini
JUPITER (Jurnal Penelitian Ilmu dan Teknologi Komputer) Vol 14 No 2-a (2022): Jupiter Edisi Oktober 2022
Publisher : Teknik Komputer Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281./4796/5.jupiter.2022.10

Abstract

Text classification can be used to organize, arrange and categorize a text. Text classification can be used for all text documents even if a text has a large number of features. However, the large number of features can cause reduced accuracy in the performance results of the classification system because there are some features that have less relevance to a text category. The Mutual Information feature selection method combined with the Support Vector Machine (SVM) algorithm is used to improve performance results in the classification process for Indonesian question documents by eliminating features with weights below the threshold. The results showed that the use of the Mutual Information feature selection method on the SVM classification algorithm was able to produce the best performance with an accuracy value of 0.92, precision: 0.93, recall: 0.89, f-measure: 0.9, computation time: 7 s and number of features: 240. Keywords— Text Classification, Feature Selection, Support Vector Machine, Mutual Information
Analisis Sentimen di Twitter Menggunakan Algoritma Artificial Neural Network Novi Yusliani; Armenia Yuhafiz; Mastura Diana Marieska; Alvi Syahrini Utami
JUPITER (Jurnal Penelitian Ilmu dan Teknologi Komputer) Vol 15 No 1d (2023): Jupiter Edisi April 2023
Publisher : Teknik Komputer Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281./6603/15.jupiter.2023.04

Abstract

Along with the development of social media, the amount of data in the form of opinions is increasing. The opinions in social media can be used to find out the assessments of social media users regarding something, one of which is the assessment of a candidate in politics. In general, the opinions in social media can be classified into two categories, namely positive and negative. Sentiment analysis is one of the research topics in the field of Natural Language Processing which aims to classify opinions into one of these categories. The opinions in social media that are often used as research objects are the opinions of Twitter users. This study uses an Artificial Neural Network (ANN) algorithm to be implemented in sentiment analysis system. The dataset used in this study is 1088 tweets consisting of 700 tweets labeled positive and 388 tweets labeled negative. The test results show that the best performance is produced when the data is divided into 80% for training and 20% for testing. The resulting percentages for each performance parameter used are accuracy is 61.3%, recall is 67.9%, precision is 75.1%, and f1-score is 71.3% using 0.01 for learning rate and 150 for epoch.
Text Generation using Long Short Term Memory to Generate a LinkedIn Post Muhammad Rizqi Assabil; Novi Yusliani; Annisa Darmawahyuni
Sriwijaya Journal of Informatics and Applications Vol 4, No 2 (2023)
Publisher : Fakultas Ilmu Komputer Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/sjia.v4i2.64

Abstract

LinkedIn is one of the most popular sites out there to advertise oneself to potential employer. This study aims to create a good enough text generation model that it can generate a text as if it were made by someone who posts on LinkedIn. This study will use a Neural Network layer called Long Short Term Memory (LSTM) as the main algorithm and the train data consists of actual posts made by users in LinkedIn. LSTM is an algorithm that is created to reduce vanishing and exploding gradient problem in Neural Network. From the result, final accuracy and loss varies. Increasing learning rate from its default value of 0.001, to 0.01, or even 0.1 creates worse model. Meanwhile, increasing dimensions of LSTM will sometimes increases training time or decreases it while not really increasing model performance. In the end, models chosen at the end are models with around 97% of accuracy. From this study, it can be concluded that it is possible to use LSTM to create a text generation model. However, the result might not be too satisfying. For future work, it is advised to instead use a newer model, such as the Transformer model.
Comparison Of Shift Reduce Parsing and Left Corner Parsing Algorithm in Sentence Structure Ambiguity Checker Reyhan Navind Shaquille; Novi Yusliani; Mastura Diana Marieska
Sriwijaya Journal of Informatics and Applications Vol 2, No 2 (2021)
Publisher : Fakultas Ilmu Komputer Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/sjia.v2i2.26

Abstract

Indonesian is the official language of the Republic of Indonesia and the language of the Indonesian nation's unity. Although it is often used, there are still errors in the use that are not in accordance with the applicable rules. One type of error is due to ambiguity which can cause misunderstandings in interpreting a word or sentence. Structural ambiguity is a type of ambiguity that occurs when the structure of words in a sentence can be given more than one grammatical structure. Left Corner Parsing and Shift Reduce Parsing are parsing methods used to classify sentence structure ambiguity. This research involves preprocessing, namely case folding, tokenizing and Part Of Speech Tagging. This study uses 90 testing data labeled with facts, 30 ambiguous sentences and 60 unambiguous sentences. Based on the results of checking the ambiguity of the sentence structure, the Shift Reduce Parsing algorithm produces an accuracy of 71%, precision 70.6%, recall 59%, and f-measure 58.2%. Meanwhile, Left Corner Parsing produces an accuracy value of 70%, precision 68.7%, recall 57.5%, and f-measure 55.8%.
Expert System to Diagnose Disease in Toddlers Using Dempster Shafer Method septi ana; Novi Yusliani; Kanda Januar Miraswan
Sriwijaya Journal of Informatics and Applications Vol 2, No 2 (2021)
Publisher : Fakultas Ilmu Komputer Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/sjia.v2i2.27

Abstract

Children, especially toddlers at the age of two months to five years old are more susceptible to disease. Limited information about diseases that attack children makes it difficult for parents to predict the disease that will suffer from their children. Therefore we need an expert system  that can predict the disease suffered by children, and the method used in this study is the Dempster Shafer method. The Dempster Shafer method can be implemented into an expert system to combine separate symptoms (evidence) in calculating the probability of a disease. Based on the test results using 250 test data, the accuracy of the expert system for diagnosing diseases in children under five years old using Dempster Shafer method is 94%.Keywords : Expert System, Dempster Shafer, Disease in Toddlers
Text Summarization with K-Means Method Ari Firdaus; Novi Yusliani; Desty Rodiah
Sriwijaya Journal of Informatics and Applications Vol 2, No 2 (2021)
Publisher : Fakultas Ilmu Komputer Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/sjia.v2i2.25

Abstract

Text Summarization is a tool used to generate a short form of text that contains important information that is needed by the user automatically. In this study, Text Summarization was conducted on Indonesian news using K-Means method. The news is taken from CNN Indonesia with a free topic. K-Means is used to classify sentences that already have weight in the news with 2 clusters, namely text summaries and not text summaries. The initial centroid is selected based on the sentence with the largest value and the sentence with the smallest value. The test conducted on Indonesian news with a total 50 news and tested for feasibility using a questionnaire. K-Means was successfully summarizing the news with an average 27.3 % of original news length and gain 87% good summarize based on respondents from questionnaire.
Classification of Emotions on Twitter using Emotion Lexicon and Naïve Bayes Dhiya Fairuz; Novi Yusliani; Kanda Januar Miraswan
Sriwijaya Journal of Informatics and Applications Vol 2, No 2 (2021)
Publisher : Fakultas Ilmu Komputer Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/sjia.v2i2.24

Abstract

Social media is a means of interaction and communication. One of the social media that is often used is Twitter. Twitter allows its users to express many things, one of which is being a personal media to provide various kinds of expressions from its users such as emotions. Users can express their emotions and sentiments through writing on the status of their social media posts. One method to find out the emotion in the sentence is using the Emotion Lexicon. However, the lexicon-based method is not good at classifying data because not every word contains emotion. So, there's a need to combine it with other classification method such as Naive Bayes. Naïve Bayes relies on independent assumptions to obtain a classification through the probability hypothesis that each class has. The results of the classification test with Emotion Lexicon alone have 46% accuracy, 45% precision, 51% recall and 36% f-measure. While the results of the classification test with Emotion Lexicon and Naïve Bayes resulted in an accuracy of 65%, precision of 77%, recall of 55%, and f- measure of 59%.
Exploring Long Short-Term Memory and Gated Recurrent Unit Networks for Emotion Classification from Electroencephalography Signals Dian Palupi Rini; Winda Kurnia Sari; Novi Yusliani; Deris Stiawan; Aspirani Utari
Scientific Journal of Informatics Vol 10, No 4 (2023): November 2023
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v10i4.47734

Abstract

This study delves into comparing LSTM and GRU, two recurrent neural network (RNN) models, for classifying emotion data through electroencephalography (EEG) signals. Both models adeptly handle sequential data challenges, showcasing their unique strengths. In EEG emotion dataset experiments, LSTM demonstrated superior performance in emotion classification compared to GRU, despite GRU’s quicker training processes. Evaluation metrics encompassing accuracy, recall, F1-score, and area under the curve (AUC) underscored LSTM’s dominance, which was particularly evident in the ROC curve analysis. This research sheds light on the nuanced capabilities of these RNN models, offering valuable insights into their efficacy in emotion classification tasks based on EEG data. The study explores parameters, such as the number of layers, neurons, and the utilization of dropout, providing a detailed analysis of their impact on emotion recognition accuracy.Purpose: The proposed model in this study is the result of optimizing LSTM and GRU networks through careful parameter tuning to find the best model for classifying EEG emotion data. The experimental results indicate that the LSTM model can achieve an accuracy level of up to 100%.Methods: To improve the accuracy of the LSTM and GRU methods in this research, hyperparameter tuning techniques were applied, such as adding layers, dense layers, flattening layers, selecting the number of neurons, and introducing dropout to mitigate the risk of overfitting. The goal was to find the best model for both methods.Results: The proposed model in this study is capable of classifying EEG emotion data very effectively. The experimental results demonstrate that the LSTM model achieves a maximum accuracy of 100%, while the GRU model achieves a highest accuracy of approximately 98%.Novelty: The novelty of this research lies in the optimization of hyperparameters for both LSTM and GRU methods, leading to the development of novel architectures capable of effectively classifying EEG emotion data.
Co-Authors Abdiansah Abdiansah, Abdiansah Abdiansyah Ahmad Fali Oklilas Aini Nabilah Al Fatih, Zaky Alvi Syahrini Alvi Syahrini Utami Angelia, Nadya Anna Dwi Marjusalinah Annisa Darmawahyuni Ari Firdaus Ari Firdaus Ari Wedhasmara Ari Widodo Ariska, Meli Armansyah, Risky Armenia Yuhafiz Aruda, Syechky Al Qodrin Aspirani Utari Astero Nandito Ayu Purwarianti Az Zahra, Lutfiah Betharia Sri Fitrianti Danny Matthew Saputra Darmawahyuni, Annisa Darmawahyuni, Annisa Deris Stiawan Desty Rodiah Desty Roodiah Dhiya Fairuz Diah Kartika Sari Dian Palupi Rini Dian Palupi Rini Dian Palupi Rini Fadel Muhammad, Fadel Firdaus Firdaus Fitria Khoirunnisa Ghita Athalina Gilbert Christopher Jambak, Muhammad Ihsan Kanda Januar Miraswan Kartika, Diah Lidya Irfiyani Silaban M Fachrurrozi M. Fachrurrozi . Mastura Diana Marieska Melly Ariska Milka, Ikbal Adrian Muhammad Fachrurrozi Muhammad Fachurrozi Muhammad Naufal Rachmatullah Muhammad Omar Braddley Muhammad Raihan Habibullah Muhammad Rizqi Assabil Muharromi Maya Agustin Nur Hamidah Nurul Izzah Oktadini, Nabila Rizky Osvari Arsalan Plakasa, Gerald Rahma Haniffia Rahmannisa, Amanda Rahmat Fadli Isnanto Raisha Fatiya Reyhan Navind Shaquille Ridho Putra Sufa Rifka Widyastuti Rizki Kurniati Rizki Ramadandi Rusdi Efendi Saputra, Danny Mathew Saputra, Danny Matthew Sari, Tri Kurnia septi ana Siti Nurmaini Syechky Al Qodrin syechky al qodrin aruda Tiara Dewangga Tristi Dwi Rizki Wenty Octaviani Winda Kurnia Sari Yenny Anwar Yesi Novaria Kunang YUNITA Yunita Yunita Yunita Yunita Yunita Yunita