Articles
<![CDATA[Sentiment Analysis of Pedulilindungi Application Reviews Using Machine Learning and Deep Learning ]]>
<![CDATA[Ahmad Rais Dwijaya]]>;
<![CDATA[Arif Dwi Laksito]]>
<![CDATA[ Jurnal Riset Informatika Vol 5 No 2 (2023): Priode of March 2023 ]]>
Publisher : <![CDATA[Kresnamedia Publisher ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.34288/jri.v5i2.505
<![CDATA[The COVID-19 pandemic that hit the world at the end of early 2020 caused many losses. The Indonesian government has established various ways to reduce the path of the COVID-19 pandemic by launching the PeduliLindungi application to reduce the spread of COVID-19. Various layers of society responded to the launch of the application with various opinions. This research mainly analyzes public opinion sentiment toward the PeduliLindungi application, as determined by 10,000 reviews on the Google Play Store. This study aims to compare the performance of deep learning and machine learning models in sentiment analysis. The stages of the research method begin with data collection methods, data pre-processing, and sentiment analysis using a machine learning model with the embedding of the word TF-IDF, which includes the Nave Bayes algorithm, Decision Tree, Random Forest, K-Nearest Neighbour, and SVM. As for the deep learning model with the fastText word embedding word representation technique using the LSTM algorithm, an evaluation is carried out using the confusion matrix. The results of this study state that deep learning models perform better than machine learning models.]]>
<![CDATA[Sentiment Analysis of Pedulilindungi Application Reviews Using Machine Learning and Deep Learning ]]>
<![CDATA[Ahmad Rais Dwijaya]]>;
<![CDATA[Arif Dwi Laksito]]>
<![CDATA[ Jurnal Riset Informatika Vol 5 No 2 (2023): Priode of March 2023 ]]>
Publisher : <![CDATA[Kresnamedia Publisher ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.34288/jri.v5i2.505
<![CDATA[The COVID-19 pandemic that hit the world at the end of early 2020 caused many losses. The Indonesian government has established various ways to reduce the path of the COVID-19 pandemic by launching the PeduliLindungi application to reduce the spread of COVID-19. Various layers of society responded to the launch of the application with various opinions. This research mainly analyzes public opinion sentiment toward the PeduliLindungi application, as determined by 10,000 reviews on the Google Play Store. This study aims to compare the performance of deep learning and machine learning models in sentiment analysis. The stages of the research method begin with data collection methods, data pre-processing, and sentiment analysis using a machine learning model with the embedding of the word TF-IDF, which includes the Nave Bayes algorithm, Decision Tree, Random Forest, K-Nearest Neighbour, and SVM. As for the deep learning model with the fastText word embedding word representation technique using the LSTM algorithm, an evaluation is carried out using the confusion matrix. The results of this study state that deep learning models perform better than machine learning models.]]>
<![CDATA[Comparative Analysis of Using Word Embedding in Deep Learning for Text Classification ]]>
<![CDATA[Mukhamad Rizal Ilham]]>;
<![CDATA[Arif Dwi Laksito]]>
<![CDATA[ Jurnal Riset Informatika Vol 5 No 2 (2023): Priode of March 2023 ]]>
Publisher : <![CDATA[Kresnamedia Publisher ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.34288/jri.v5i2.507
<![CDATA[A group of theory-driven computing techniques known as natural language processing (NLP) are used to interpret and represent human discourse automatically. From part-of-speech (POS) parsing and tagging to machine translation and dialogue systems, NLP enables computers to carry out various natural language-related activities at all levels. In this research, we compared word embedding techniques FastText and GloVe, which are used for text representation. This study aims to evaluate and compare the effectiveness of word embedding in text classification using LSTM (Long Short-Term Memory). The research stages start with dataset collection, pre-processing, word embedding, split data, and the last is deep learning techniques. According to the results of the experiments, when compared to the glove technique it seems that FastText is superior, the accuracy obtained reaches 90%. The number of epochs did not significantly improve the accuracy of the LSTM model with GloVe and FastText. It can be concluded that the FastText word embedding technique is superior to the GloVe technique.]]>
<![CDATA[Comparative Analysis of Using Word Embedding in Deep Learning for Text Classification ]]>
<![CDATA[Mukhamad Rizal Ilham]]>;
<![CDATA[Arif Dwi Laksito]]>
<![CDATA[ Jurnal Riset Informatika Vol 5 No 2 (2023): Priode of March 2023 ]]>
Publisher : <![CDATA[Kresnamedia Publisher ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.34288/jri.v5i2.507
<![CDATA[A group of theory-driven computing techniques known as natural language processing (NLP) are used to interpret and represent human discourse automatically. From part-of-speech (POS) parsing and tagging to machine translation and dialogue systems, NLP enables computers to carry out various natural language-related activities at all levels. In this research, we compared word embedding techniques FastText and GloVe, which are used for text representation. This study aims to evaluate and compare the effectiveness of word embedding in text classification using LSTM (Long Short-Term Memory). The research stages start with dataset collection, pre-processing, word embedding, split data, and the last is deep learning techniques. According to the results of the experiments, when compared to the glove technique it seems that FastText is superior, the accuracy obtained reaches 90%. The number of epochs did not significantly improve the accuracy of the LSTM model with GloVe and FastText. It can be concluded that the FastText word embedding technique is superior to the GloVe technique.]]>
<![CDATA[Hate speech detection on Indonesian text using word embedding method-global vector ]]>
<![CDATA[Mardhiya Hayaty]]>;
<![CDATA[Arif Dwi Laksito]]>;
<![CDATA[Sumarni Adi]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 12, No 4: December 2023 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v12.i4.pp1928-1937
<![CDATA[Hate speech is defined as communication directed toward a specific individual or group that involves hatred or anger and a language with solid arguments leading to someone's opinion can cause social conflict. It has a lot of potential for individuals to communicate their thoughts on an online platform because the number of Internet users globally, including in Indonesia, is continually rising. This study aims to observe the impact of pre-trained global vector (GloVe) word embedding on accuracy in the classification of hate speech and non-hate speech. The use of pre-trained GloVe (Indonesian text) and single and multi-layer long short-term memory (LSTM) classifiers has performance that is resistant to overfitting compared to pre-trainable embedding for hatespeech detection. The accuracy value is 81.5% on a single layer and 80.9% on a double-layer LSTM. The following job is to provide pre-trained with formal and non-formal language corpus; pre-processing to overcome non-formal words is very challenging.]]>
<![CDATA[Implementasi Aplikasi Sentimen Pada Data Twitter Jelang Pemilu 2024 ]]>
<![CDATA[Choirul Humam]]>;
<![CDATA[Arif Dwi Laksito]]>
<![CDATA[ Jurnal Informatika: Jurnal Pengembangan IT Vol 8, No 2 (2023) ]]>
Publisher : <![CDATA[Politeknik Harapan Bersama ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30591/jpit.v8i2.5051
<![CDATA[Elections are one of the most important democratic processes, giving citizens the right to choose their leaders. In today's digital era, social media is an increasingly important information source influencing public perception. Twitter has been a social media from the past until now that still exists in finding information. Tweets are one of the most frequently used services to express opinions or opinions to the public. Sentiment analysis as an application of Natural Language Processing (NLP) is helpful in understanding public opinion towards prospective leaders and issues discussed during election campaigns. The motivation for this study is to conduct text classification using a deep learning model called LSTM and to compare the use of oversampling and non-oversampling methods. This research started by collecting datasets from Twitter, labelling, pre-processing, creating and evaluating the model, and implementing it into the web application. The experiment showed that the random oversampling technique gets more significant accuracy than non-oversampling. Random oversampling produces an accuracy of 0.82 at epoch 25, while non-oversampling reaches an accuracy of 0.61 at epoch 50]]>
<![CDATA[Object Recognition with SSD MobileNet Pre-Trained Model in the Cashier Application ]]>
<![CDATA[Burhanudin, Nazil Ilham]]>;
<![CDATA[Laksito, Arif Dwi]]>;
<![CDATA[Sidauruk, Acihmah]]>;
<![CDATA[Yudianto, Muhammad Resa Arif]]>;
<![CDATA[Rahmi, Alfie Nur]]>
<![CDATA[ Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol 12, No 2 (2023): JULI ]]>
Publisher : <![CDATA[ISB Atma Luhur ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32736/sisfokom.v12i2.1659
<![CDATA[Object recognition is a type of image processing technique that is frequently employed in current applications such as facial identification, vehicle detection, and automated cashiers. One issue with barcode and RFID cashier apps is that they cannot scan several products at the same time. The cashier application employing object identification using picture images is believed to be able to distinguish more than one object in order to speed up the transaction process. The usage of SSD pre-trained models with MobileNet architecture to detect items in automatic cashier applications is discussed in this paper. This study put the model to the test on three types of soft drink objects: coca-cola, floridina, and good day. A smartphone camera was used to collect the data, which totaled 203 images. The findings indicated that the product object identification method was 82.9% accurate, 97.5% precise, and 84.7% recall. The object recognition process takes between 365 and 827 milliseconds, with an average time of 695 milliseconds (0.69 seconds).]]>
<![CDATA[Usability Testing on QR Code Scanner Application for Lecture Presence ]]>
<![CDATA[Pujastuti, Eli]]>;
<![CDATA[Laksito, Arif Dwi]]>
<![CDATA[ Khazanah Informatika Vol. 6 No. 1 April 2020 ]]>
Publisher : <![CDATA[Department of Informatics, Universitas Muhammadiyah Surakarta, Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.23917/khif.v6i1.9026
<![CDATA[Universities are obliged to facilitate lectures. Many students require universities to provide a fair teaching and learning services with a minimum of student cheating. In order to improve the quality of teaching and learning, each university develops a lecture presence system electronically. The QR code scanner application became a solution offered for leak problems that previously existed on the magnetic card system. Before the application applied on a large scale, developers needed to conduct an assessment of the usability of the QR scanner application. The assessment aimed to make lectures go smoothly and to maintain the good reputation of the university. The method used is usability testing. The result of this study is a usability system at the level of 65%. This value consists of an effectiveness value of 70%, an efficiency value of 54.31%, and a satisfaction value of 70.85%. The improvements of user interface recommended in this study include adding of placeholders to inform the correct NIM format, changing the QR scanner icon into a titled icon and choosing a stimulating color, providing a zoom feature on the scanner camera, and applying a more familiar logout icon according to the mental model of the user.]]>
<![CDATA[Analisis Perbandingan Ekstraksi Fitur Teks pada Sentimen Analisis Kenaikan Harga BBM ]]>
<![CDATA[Darmawan, Briga]]>;
<![CDATA[Laksito, Arif Dwi]]>;
<![CDATA[Yudianto, Muhammad Resa Arif]]>;
<![CDATA[Sidauruk, Acihmah]]>
<![CDATA[ Krea-TIF: Jurnal Teknik Informatika Vol 11 No 1 (2023) ]]>
Publisher : <![CDATA[Fakultas Teknik dan Sains, Universitas Ibn Khaldun Bogor ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32832/krea-tif.v11i1.13819
<![CDATA[BBM merupakan bahan bakar yang digunakan kendaraan bermotor. Penggunaan BBM meningkat sejalan dengan pertumbuhan ekonomi di Indonesia. Kenaikan harga BBM di Indonesia menimbulkan berbagai macam pendapat di media sosial twitter melalui posting dan thread. Fokus penelitian ini melakukan analisis sentimen terhadap kenaikan BBM yang datanya didapat melalui twitter dengan jumlah 1667 data. Tujuan dari penelitian ini melakukan perbandingan metode ekstraksi fitur yang memiliki kinerja paling baik seperti TF-IDF, Bag of Word, dan FastText diuji dengan algoritma machine learning SVM. Untuk tahap penelitian yang pertama melakukan crawling data twitter, preprocessing data, ekstraksi fitur, pembuatan model dengan algoritma machine learning, dan kemudian dilakukan pengujian dan perbandingan model confusion matrix pada setiap ekstraksi fitur. Hasil dari penelitian ini menunjukkan bahwa penggunaan ekstraksi fitur BoW memiliki kinerja lebih baik dibandingkan model ekstraksi fitur yang lain.]]>
<![CDATA[IDENTIFIKASI FUNGSI PERKOTAAN KAWASAN KOTABARU, KOTA YOGYAKARTA MENGGUNAKAN DATA SURVEI LAPANGAN DAN POINT OF INTEREST GOOGLE MAPS ]]>
<![CDATA[Kartikakirana, Renindya Azizza]]>;
<![CDATA[Laksito, Arif Dwi]]>;
<![CDATA[Adninda, Gardyas Bidari]]>;
<![CDATA[Rifani, Irfan]]>
<![CDATA[ Jurnal Pengembangan Kota Vol 12, No 2: Desember 2024 ]]>
Publisher : <![CDATA[Diponegoro University ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.14710/jpk.12.2.162-173
<![CDATA[Identifikasi fungsi kota yang akurat dan efektif sangat penting untuk mengoptimalkan pengalokasian tata ruang kota dan memonitoring perkembangan kota, termasuk di Kawasan Kotabaru, Yogyakarta. Penelitian ini berusaha membandingkan hasil antara 2 metode identifikasi fungsi perkotaan, yaitu interpretasi citra disertai survei lapangan dan data Point of Interest (POI). Penelitian ini menggunakan pendekatan deduktif-kuantitatif-kualitatif. Berdasarkan hasil penelitian diperoleh bahwa terdapat perbedaan hasil identifikasi fungsi perkotaan Kawasan Kotabaru antara metode identifikasi melalui interpretasi citra disertai survei lapangan dan data Point of Interest (POI). Perbedaan hasil ini dikarenakan POI yang diperoleh dari google maps secara gratis hanya 60 POI (tidak semua POI pada kawasan). Adapun metode identifikasi fungsi perkotaan yang lebih efektif dari segi output yang dihasilkan yaitu metode interpretasi citra disertai survei lapangan. Dari segi efektivitas waktu dan efisiensi biaya, metode yang lebih baik yaitu metode data POI. Dengan demikian, dapat disimpulkan bahwa untuk memperoleh data yang akurat lebih baik menggunakan metode interpretasi disertai validasi survei lapangan. Namun jika untuk memonitoring perkembangan kota secara cepat dan murah, maka metode data POI lebih baik digunakan dari pada metode interpretasi disertai survei lapangan.]]>
