Sistem Infomasi

Permanent URI for this collection

https://repository.unri.ac.id/handle/123456789/2385

Browse

Browsing Sistem Infomasi by Author "Aminuddin, Al"

Now showing 1 - 7 of 7
  • No Thumbnail Available
    Item
    ANALISIS PENENTUAN DOSEN PEMBIMBING SKRIPSI MAHASISWA MENGGUNAKAN NAIVE BAYES CLASSIFIER
    (2020-09) Rahayu, Sri; Fatayat, Fatayat; Salambue, Roni; Aminuddin, Al
    Determination of the mentor lecturer for students is very influential in completing the final task. Lecturers who are competent and in accordance with the field of student's final assignment able to direct of the student's final assignment. In this thesis, text mining is used to classify the appropriate guidance lecturers for students in completing the final assignment. Classification is applied to the title of the student's final assignment based on experience and field of mentor lecturers. The algorithm used naive bayes classifier algorithm. Before the data classification processed at the text preprocessing stage, which consist of case folding, stopcharacter removal, stopword, stemming, and weighted. Evaluation to measure the accuracy of this system using confussion matrix which resulted in 78% accuracy in mentor lecturers and generate acuration of 95% in field of expertise.
  • No Thumbnail Available
    Item
    Analisis Sentimen Pengguna Terhadap Aplikasi Netflix di Google Play Store Menggunakan Support Vector Machine
    (Elfitra, 2023-03) Azura, Endah; Aminuddin, Al
    During the COVID-19 pandemic, one of the activities commonly carried out by the community, such as going out of the house, was limited by the PSBB (Large-Scale Social Restrictions). This made people stay at home more and use internet access, one of which was by streaming movies using the Netflix application. Users can provide reviews of application services in the review feature on the Google Play Store. The existence of this feature is one of the considerations for prospective users to download the application. Therefore it is necessary to do sentiment analysis to find out how the user's sentiment is on the application. Therefore, this study aimed to analyze reviews and discovered the results of the accuracy of public sentiment reviews on a movie streaming application, namely Netflix on the Google Play Store using the Support Vector Machine method. In this study, data collection was carried out using web scraping techniques on Google Colaboratory. The data used was data when the pandemic spread to Indonesia, namely in 2020. The method used in this study resulted in an average accuracy of 85%.
  • No Thumbnail Available
    Item
    ANALISIS SENTIMEN PENGGUNA TWITTER TERHADAP APLIKASI MYPERTAMINA MENGGUNAKAN METODE K-NEAREST NEIGHBOR DENGAN SELEKSI FITUR CH-SQUARE
    (Elfitra, 2023-03) Miranda, Dynda Chintya; Aminuddin, Al
    Pertamina announced a trial policy for using the MyPertamina application for targeted distribution of subsidized fuel in June 2022. This trial was carried out in 11 regions started on July 1, 2022. This policy had been widely discussed on social media Twitter, so there are pros and cons from the community. The large number of public responses in the form of tweets on Twitter requires a sentiment analysis to see an overview of the public's perception of the MyPertamina application. This study used the K-Nearest Neighbor algorithm to classify the public's response to the policy in the form of positive or negative sentiment. This study also added the Chi-Square selection feature to determine the effect on the performance of the K-Nearest Neighbor algorithm. This study used the Python programming language with 2923 tweets as a dataset which had a proportion of 73% positive sentiment and 27% negative sentiment. The research used ratio of 80:20 to the dataset, namely 80% of the training data is 2338 and 20% of the testing data is 585. The resulted of the research on the K-Nearest Neighbor algorithm used K-Fold Cross Validation for 10 broadcasts produced the same average accuracy, namely 77% for both methods, which had the highest accuracy of 88% for K-Nearest Neighbor with Chi-Square and 87% accuracy without used Chi-Square.
  • No Thumbnail Available
    Item
    ANALISIS SENTIMEN ULASAN PENGGUNA TERHADAP APLIKASI LINKEDIN MENGGUNAKAN PENDEKATAN BERT
    (Elfitra, 2023-06) Putri, Rahmadea; Aminuddin, Al
    Google Play Store, one of the largest digital distribution platforms for downloading and uploading developed applications, was the focus of this research aimed at obtaining sentiment analysis results of LinkedIn application users. Sentiment analysis was used to evaluate the response of LinkedIn users and enable developers to improve the quality of LinkedIn applications in the future. User review data was collected through the scraping method and included 4,333 reviews, of which 2,296 were positive, 543 were neutral, and 1,494 were negative. Positive sentiments dominated the proportion of sentiments, at 53%. The model and method used for analysis were the pre-trained BERT model, known as IndoBERT, with average accuracies of 84% for validation data, respectively. An evaluation of the model through a confusion matrix yielded an accuracy of 80%, precision of 90%, recall of 84%, and F1-Score of 87%.
  • No Thumbnail Available
    Item
    Implementasi Text Mining Dengan Random Forest Untuk Analisa Sentimen Tanggapan Masyarakat Di Twitter Terhadap RKUHP 2022
    (Elfitra, 2023-05) Liswandi, Hendra; Aminuddin, Al
    Indonesia is a state of the law as stipulated in Article 1 paragraph (3) of the third amendment of the 1945 Constitution. The state sets rules and policies to regulate society. The power exercised by the government/ruler can be interpreted as state action. This includes the enactment of the Criminal Code, commonly known as the Criminal Code, which is confirmed by Law Number 73 of 1958 concerning the enactment of Law Number 1 of 1946 of the Republic of Indonesia concerning criminal law regulations for the entired territory of the Republic of Indonesia and amending the Criminal Code. The Draft Criminal Code (RKUHP), which has not yet been ratified, has drawn a lot of criticism in Indonesia because it is considered over criminalization. The amount of criticism conveyed by the public has caused the RKUHP to become one of the trending topics or the most frequently discussed topics in 2022. The Draft Criminal Code will be passed in July 2022 by the government and the House of Representatives. One of the articles that are being discussed by the public is the punishment for people who insult the government, especially on social media. Some people think that the article deviates from Indonesia's democratic system. With the advancement of technology, many people complain about the changes in the Criminal Code on social media, especially Twitter. Therefore, the researcher aimed to determine the accuracy of the results of public sentiment toward the 2022 Criminal Code on Twitter used the Random Forest method. In this study, data collection used a snsscraper in jupyter notebook. The data used was data from October 2022 to November 2022. This method produced the highest accuracy of 0.81 at the 7th index and the lowest accuracy is 0.61 at the 4th index.
  • No Thumbnail Available
    Item
    SISTEM INFORMASI GEOGRAFIS PEMETAAN LAHAN DAN HASIL PRODUKSI KELAPA MENGGUNAKAN METODE KMEANS
    (Elfitra, 2023-06) Astianti, R. Chyntia; Aminuddin, Al
    Coconut is a variety of plant from the Arecaceae family that has various benefits almost from all parts. Indragiri Hilir regency consists of 20 districts with abundant coconut plantation land potential. The purpose of this research was to determine and classify the location of coconut plantation land and production results in map visualization and the application of K-Means Clustering Algorithm. This system was designed using UML diagrams, Laravel framework, and MySQL database. The results obtained from this study was that the 20 districts in Indragiri Hilir Regency are divided into 3 clusters. Of these three clusters, cluster 3 was the highest potential for coconut plantation land with a total of 5 districts as cluster members.
  • No Thumbnail Available
    Item
    SISTEM PAKAR DIAGNOSA PENYAKIT INFEKSI SALURAN PERNAPASAN AKUT (ISPA) MENGGUNAKAN METODE FORWARD CHAINING BERBASIS ANDROID
    (Elfitra, 2023-06) Akbar, Rivki; Aminuddin, Al
    The utilization of information technology played a significant role in handling various diseases, one of which is the respiratory tract infection (ISPA) disease. The emergence of information technology in the healthcare sector had driven the development of expert system applications for healthcare services. This research used the forward chaining method, which was the process of drawing conclusions based on existing data leading to a conclusion. The expert system that was created by an android-based expert system. By using 10 diseases and 40 data symptoms of ISPA diseases, this research successfully implemented an expert system for disease diagnosis based on android by taking the highest calculation percentage. Based on the UAT results, it could be concluded that the ISPA diseases expert system application had an attractive interface, was easy to use, features on the system were easy to understand, the list of disease symptom evaluations was appropriate according to the health canter standards, and the diagnosis results were appropriate based on the disease symptoms.

We collect and process your personal information for the following purposes: Authentication, Preferences, Acknowledgement and Statistics.
To learn more, please read our privacy policy.

Customize