Claim Missing Document
Check
Articles

Found 37 Documents
Search

Indonesian News Text Summarization Using MBART Algorithm Astuti, Rahma Hayuning; Muljono, Muljono; Sutriawan, Sutriawan
Scientific Journal of Informatics Vol 11, No 1 (2024): February 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i1.49224

Abstract

Purpose: Technology advancements have led to the production of a large amount of textual data. There are numerous locations where one can find textual information sources, including blogs, news portals, and websites. Kompas, BBC, Liputan 6, CNN, and other news portals are a few websites that offer news in Indonesian. The purpose of this study was to explore the effectiveness of using mBART in text summarization for Bahasa Indonesia.Methods: This study uses mBART, a transformer architecture, to perform fine-tuning to generate news article summaries in Bahasa Indonesia. Evaluation was conducted using the ROUGE method to assess the quality of the summaries produced.Results: Evaluation using the ROUGE metric showed better results, with ROUGE-1 of 35.94, ROUGE-2 of 16.43, and ROUGE-L of 29.91. However, the performance of the model is still not optimal compared to existing models in text summarization for another language.Novelty: The novelty of this research lies in the use of mBART for text summarization, specifically adapted for Bahasa Indonesia. In addition, the findings also contribute to understanding the challenges and opportunities of improving text summarization techniques in the Indonesian context.
INFLASI, TINGKAT SUKU BUNGA DAN NILAI TUKAR TERHADAP RETURN SAHAM Setyaningrum, Rani; Muljono, Muljono
Jurnal Analisis Bisnis Ekonomi Vol 14 No 2 (2016)
Publisher : Universitas Muhammadiyah Magelang

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

Abstract

Penelitian ini menggunakan data sekunder. Beberapa data yang digunakan dalam penelitian ini adalah data return saham, infl asi, tingkat suku bunga, dan nilai tukar periode 2013-2015. Data-data tersebut diperoleh dari publikasi-publikasi yang diterbitkan BEI dan Bank Indonesia. Teknik analisis yang dipakai dalam penelitian ini adalah regresi linear berganda untuk memperoleh gambaran yang menyeluruh mengenai hubungan antara variabel satu dengan yang lain. Uji hipotesis menggunakan Uji-t untuk menguji pengaruh variabel variabel secara parsial dan Uji F untuk menguji variabel secara bersama-sama terhadap return saham dengan tingkat signifi kansi 0,05. Selain itu dilakukan uji asumsi klasik meliputi uji multikolinearitas, uji autokorelasi, uji heteroskedastisitas dan uji normalitas. Berdasarkan hasil penelitian secara simultan tiga variabel yaitu infl asi, tingkat suku bunga, dan nilai tukar berpengaruh terhadap return saham secara signifi kan dengan nilai F sebesar 0,024. Berdasarkan hasil penelitian secara parsial variabel infl asi dan nilai tukar tidak berpengaruh terhadap return saham secara signifi kan dengan nilai masing-masing infl asi (0,121) dan nilai tukar (0,062). Sedangkan tingkat suku bunga berpengaruh terhadap return saham secara signifi kan dengan arah negatif sebesar (0,004).
ANALISIS PENGARUH FAKTOR-FAKTOR FUNDAMENTAL TERHADAP PRICE TO BOOK VALUE PADA INDUSTRI BARANG KUNSUMSI DI BEJ Muljono, Muljono; Prasetyo, Prasetyo
Jurnal Analisis Bisnis Ekonomi Vol 3 No 1 (2005)
Publisher : Universitas Muhammadiyah Magelang

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

Abstract

Price to book value repesent one of variable which can be used for the decision making of in doing an invesment. Price to book value used to identify an sahre price by comparing with its book value. This research aim to test to return the research conducted by A.Y.B Santosa (1997) and also give the empirical evidence for factors influencing price to book value. This research is used to know the influence of factors fundamental that is : Dividend Payout Ratio, Financial Laverage, Earning Growth Rate, and Return On Equity to Price to Book Value. This Research also aim to know he most dominant variable its link by price is to book value. Data used in this research is secondary data that is in the form of data of time series-ross section consisted of by 10 companies deputizing taht is peripatetic company at industrial sector cunsumer goods. Method of data collecting use the method of purposing sampling. While technical analyze in this research use the technique analyze the doubled linear regresi to know the independent variable influence to variable of dependennya and technique analyze the correlation coefficient of parsial used to know the modt dominant independent variable dependennya. To test the hypothesis use the test F, the test t, and test the determinant which is entire/all its processing is conducted by using SPSS version 10.0 windows. Result of data analysis with the technique analyze the multiple linear regression indicate that by simultan is price to book value influenced by its his independent variable that is: Dividend Payout Ratio, Financial Laverage, Earning Growth Rate, and Return On Equity. Assess the Adjusted R2 of equal to 0,242 showing change PBV influenced by together equal to 24,2% by variable DPR.
DETERMINAN FLUKTUASI HARGA SAHAM SEKTOR KEUANGAN YANG TERDAFTAR DI BURSA EFEK INDONESIA Muljono, Muljono
Jurnal Analisis Bisnis Ekonomi Vol 6 No 1 (2008)
Publisher : Universitas Muhammadiyah Magelang

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

Abstract

This research is aimed at analyzing influence of several factor on stock price fluctuation of financial sectors on 2004 up to 2005 in BEJ. The research result show that from the six factors assumed to influence on stock price fluctuations of financial sectors under investigation, there are Price Earning Ratio (PER), Earning Per Share (EPS), Book Value (BV), Return on Invesment (ROI), Return on Equity (ROE) and interest rate. The sample was taken by using purposive sampling polling data method. The population cover 130 companie, while the taken sample consist of 42 companies, the research period of 2 years (2004 up to 2005). The data were analyzed by double regression model. It empirically is found taht Earning Per Share (EPS) significant influences on stock price fluctuations. Based on the research result it is also dicovered that Price Earnning Ratio (PER), Earning Per Share (EPS), Book Value (BV), Return on Invesment (ROI), Return on Equity (ROE) and interest rate have weak influencce in explaining stock price fluctuation variation at the Indonesian capital market, in which Adjusted R2 is only 37.7 which the means taht stock price fluctuations is mostly determined by market psycology, that is not fundamental factors.
DETERMINAN RISIKO SISTEMATIS PERUSAHAAN MANUFAKTUR YANG TERDAFTAR DI BURSA EFEK JAKARTA TAHUN 2003-2005 Muljono, Muljono
Jurnal Analisis Bisnis Ekonomi Vol 5 No 2 (2007)
Publisher : Universitas Muhammadiyah Magelang

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

Abstract

This research represent the event study with the approach of case study of at Indonesia Stock Exchange using historical data of year 2003-2005. Sample will be taken by purposive sampling and company in Indonesia Stock Exchange. Analysis used in this research is multiple regression. The research was aimed at evaluating empirically the effects of five independent variable that included dividend pay out Ratio, leverage, earning, variability, liquidity and asset size on sistematic risk. The contribution of independent variables on dependent ones is indicated by determination coefficient test (R2 test). t test and F test were applied to evaluate the hypothesis. In a simultan earning dividend pay out Ratio, leverage, earning, variability, liquidity and asset size having not significant influence to a sistematic risk (beta). The research is more influenced by the other variables exluded in the study.
Algoritma Naive Bayes Untuk Memprediksi Bimbingan Konseling Siswa Sekolah Menengah Kejuruan Adawiyah, Robiatul; Muljono, Muljono; Nugroho, Wildani Eko
Smart Comp :Jurnalnya Orang Pintar Komputer Vol 12, No 3 (2023): Smart Comp: Jurnalnya Orang Pintar Komputer
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/smartcomp.v12i3.5365

Abstract

Masalah bimbingan konseling merupakan masalah yang terdapat pada sekolah yang susah untuk di tebak. Prediksi yang akurat diperlukan bagi pengambil kebijakan untuk mengambil keputusan terkait pengolahan data siswa. Peramalan jangka pendek untuk panduan dan saran menggunakan Naïve Bayes sebagai model terapan. Untuk mengimplementasikan Naïve Bayes, kita perlu menentukan beberapa parameter. Oleh karena itu, diperlukan perhitungan untuk menerapkan metode peramalan dengan menggunakan teknik data mining. Oleh karena itu, untuk mengatasi masalah tersebut diperlukan suatu metode yang sesuai agar parameters yang diperoleh lebih optimal. Salah satu teknik data mining adalah Naïve Bayes yang menggunakan teknik klasifikasi, yang mampu menghasilkan nilai akurasi sebesar 90.46%.
Comparative Analysis of IndoBERT and Classic Machine Learning Models for Sentiment Classification of Education Policy on Social Media X Medantoro, Gabriella Fani Suciarti; Muljono, Muljono
Journal of Applied Informatics and Computing Vol. 10 No. 1 (2026): February 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i1.11723

Abstract

Leadership changes provide an opportunity for new education policies, generating complex public opinions on social media X that often contain implicit sentiments like satire, making automated analysis challenging. This study aims to address this challenge by conducting a comparative analysis to evaluate the effectiveness of the IndoBERT model in capturing nuanced, implicit sentiments compared to traditional machine learning classifiers (SVM, Naïve Bayes, Logistic Regression, KNN, and Random Forest). This research utilized a dataset of Indonesian-language tweets, collected via crawling. Data was pre-processed (cleaning, case folding, etc.) and labeled (positive/negative) using a hybrid Lexicon-LLM approach. The TF-IDF technique was used for feature extraction for the machine learning models, while IndoBERT used its internal tokenization. Models were evaluated using accuracy, precision, recall, and F1-score. The results showed that the IndoBERT model performed best with an accuracy score of 97%, significantly outperforming the other best machine learning models, namely Random Forest 95% and SVM 95%. This study concludes that the IndoBERT model is a superior and more robust solution for analyzing nuanced public sentiment on educational policies, demonstrating a greater ability to understand complex context and implicit language compared to traditional TF-IDF-based methods.