Sentiment analysis digunakan untuk melihat opini terhadap sebuah masalah menuju ke opini positif atau negatif. Media sosial Twitter merupakan salah satu media yang digunakan untuk memberikan opini melalui tweet. Pengguna Twitter akan memberikan opini tentang suatu hal, salah satunya film yang sedang tayang di bioskop. Opini pengguna bermanfaat bagi pengguna lain dan rumah produksi film berkaitan evaluasi film. Klasifikasi opini diperlukan untuk memudahkan pengguna dalam melihat opini positif, negatif, atau netral. Algoritma yang digunakan dalam klasifikasi adalah Support Vector Machine. Dataset berjumlah 1.027 tweet yang didapatkan dari tweet untuk film populer tahun 2016. Hasil klasifikasi opini terbagi menjadi 3, yaitu opini positif, negatif, dan netral. Evaluasi menentukan tingkat akurasi dari algoritma Support Vector Machine. Hasil akurasi klasifikasi algoritma Support Vector Machine menggunakan 60, 70, 80, dan 90 persen data training rata- ratanya adalah 76,06 persen, 76,83 persen, 81,07 persen, dan 83,3 persen. Nilai precision positif memiliki rata- rata sebesar 79,97 persen, 78,71 persen, 84,02 persen, dan 85,54 persen. Nilai precision negatif memiliki rata- rata sebesar 81,73 persen, 87,41 persen, 87,37 persen, dan 93,61 persen. Nilai precision netral memiliki rata- rata sebesar 67,13 persen, 69,47 persen, 74,08 persen, dan 74,14 persen.
Pelayanan instansi pemerintah menjadikan tolok ukur dalam menilai tingkat kepuasan masyarakat. Instansi pemerintah di Indonesia perlahan telah memanfaatkan media sosial sebagai sarana komunikasi dengan masyarakat. Karena media sosial mendapatkan tempat yang istimewa pada penggunaan internet di Indonesia. Terutama media sosial, khususnya untuk Youtube yang mana sekarang segala sesuatunya dapat diupload setiap saat dan berjuta komentar diunggah pada media berbagi video. Penelitian ini mencoba melakukan Analisa sentimen menggunakan klasifikasi data Youtube pada komentar video yang dipublish pemerintah tentang kinerjanya kepada masyarakat. Data tersebut nantinya akan diklasfikasikan menjadi klasifikasi positif, negatif dan netral. Komentar tersebut kemudian diproses menggunakan metode Naïve Bayes Classifier. Hasil dari pengujian yang dilakukan memperoleh nilai akurasi sebesar untuk KemenPUPR 69.23% dan 64.10% untuk Kemenkeu. Kata kunci : Pelayanan, Analisis Sentimen, Naive Bayes Classifier
Melihat pola kehidupan manusia saat ini menunjukkan bahwa aktivitas sehari-hari tidak dapat dipisahkan dari internet. Gaya hidup ini secara tidak langsung memengaruhi cara seseorang berkomunikasi. Di internet, banyak sekali pendapat, kritik atau saran digunakan untuk menilai kinerja organisasi. Organisasi yang disebutkan adalah organisasi perbankan yang dimiliki pemerintah yang memberikan layanan kepada publik. Penelitian ini mengembangkan sistem yang dapat memberikan penilaian terhadap kinerja organisasi mengggunakan pendapat masyarakat pada perbankan pemerintah. Algoritma yang digunakan dalam penelitian ini adalah Rating System Based On Adjective. Jumlah pengambilan data adalah 10, 30 dan 50 pada pencarian data pertama. Pencarian data diperoleh dengan crawling data online memanfaatkan API Google di situs web atau blog di internet. Proses pengujian algoritme menggunakan "ulasan kinerja pada bank yang dicari" dalam 10 pencarian pertama adalah 98,59% dengan kesalahan persentase 45,2. Proses pengujian algoritma dalam 30 pencarian pertama adalah 99,84% dengan kesalahan persentase 40,04. Proses pengujian algoritma dalam 50 pencarian pertama adalah 98,21% dengan kesalahan persentase 30,73.
This research aims to examine the role of job satisfaction in compensation, environment, discipline, and performance in Indonesia Higher Education, exactly in State Polytechnic of Banjarmasin (POLIBAN). To examine the hypotheses and mediator variabel, this research used <em>Partial Least Square</em> (PLS)<em>.</em> It found that of ten hypotheses tested, four hypeteses were negative and insignificant. In addition, the test of mediation, by PLS, also showed that Job satisfaction cannot mediate the relationship between compensation and performance. However, it can be a mediator for the relationship between environment or discipline and performance. These results confirmed and contradict to the previous studies conducted.
Nowadays, biometric modalities have gained popularity in security systems. Nevertheless, the conventional commercial-grade biometric system addresses some issues. The biggest problem is that they can be imposed by artificial biometrics. The electroencephalogram (EEG) is a possible solution. It is nearly impossible to replicate because it is dependent on human mental activity. Several studies have already demonstrated a high level of accuracy. However, it requires a large number of sensors and time to collect the signal. This study proposed a biometric system using single-channel EEG recorded during resting eyes open (EO) conditions. A total of 45 EEG signals from 9 subjects were collected. The EEG signal was segmented into 5 second lengths. The alpha band was used in this study. Discrete wavelet transform (DWT) with Daubechies type 4 (db4) was employed to extract the alpha band. Power spectral density (PSD) was extracted from each segment as the main feature. Linear discriminant analysis (LDA) and support vector machine (SVM) were used to classify the EEG signal. The proposed method achieved 86% accuracy using LDA only from the third segment. Therefore, this study showed that it is possible to utilize single-channel EEG during a resting EO state in a biometric system.
The plagiarism of scientific work, especially undergraduate thesis, mostly happened in the college. In this research we used text mining, a new method which can be used to do the checking procedure, to obtain specific pattern of the document. After obtaining the document pattern, we compare the pattern with another document pattern. If the level of pattern similarity is high, it can be suspected as plagiarism. This paper will explain the development of the text preprocessing, a part of text mining. We choosed Nazief and Adriani Algorithm as a text preprocessing algorithm for this research. This research will result a text preprocessing web service. The web service is expected to be used for further development of text mining.
In the Law Fiction Theory, it is assumed that once the government enforces legal norms at that time, everyone is considered to know the law. So that someone’s ignorance of the law cannot free him from lawsuits. This condition led to the emergence of legal cases caused by a lack of public understanding of the law. This paper introduces a potential solution by providing chatbots platforms. We propose chatbots designed to provide information, for those who need information about applicable laws. Users can ask about anything about applicable legal documents. Furthermore, the bot performs a search according to requests related to legal documents. Various request commands are given so that bots can behave like humans and provide the information needed by users. The experimental results have shown that chatbot could recognize all of the questions from user and could answer correctly.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.