Claim Missing Document
Check
Articles

Found 5 Documents
Search
Journal : Intelmatics

A Web-Based Boarding Management Application Design Maulana, Muhamad Anggi; Syaifudin; Sari, Syandra; Najih, Muhammad
Intelmatics Vol. 4 No. 1 (2024): Januari-Juni
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/itm.v4i1.17649

Abstract

In Indonesia, the rental business of temporary accommodations or boarding houses ('kost') has significantly grown due to the influx of individuals from various cities or regions seeking temporary residence for educational pursuits, work, entrepreneurship, or marriage. Boarding house owners often manage not just one or two rooms but can have dozens or even hundreds of rooms. This extensive scale makes it challenging for boarding house owners to efficiently handle payment data, accurately record information, and report room damages using conventional methods. To address these challenges, an application was developed to streamline data management for boarding house owners, enabling them to efficiently manage their businesses. The data collection methods employed for developing this application included observation, interviews, and literature review, following the waterfall model for software development. The obtained results from this application development facilitate better service management for boarding house owners, enhancing cost and time efficiency while improving the quantity and quality of managed information.
PERFORMANCE COMPARISON OF TWITTER SENTIMENT ANALYSIS USING FASTTEXT SVM AND TF-IDF SVM: A CASE STUDY ON ELECTRIC MOTORCYCLES Sulaba, Wishnu Abhinaya; Solihah, Binti; Sari, Syandra
Intelmatics Vol. 4 No. 2 (2024): Juli-Desember
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/v4i2.18145

Abstract

Electric motorcycles are trending on Twitter as two-wheeled vehicles different from those using fossil fuels. Electric motorcycles rely on batteries charged using electricity. However, there are many opinions about electric motorcycles on social media, especially Twitter. Yet, tweets and comments on Twitter often contain irrelevant words that can affect sentiment analysis. In this study, sentiment analysis was conducted on 8,000 data from Twitter using FastText and TF-IDF as word embedding techniques, along with Support Vector Machine (SVM) as the classification technique. The aim of this research is to compare the performance of SVM using different feature extraction techniques, namely FastText and TF-IDF. The results of this study are expected to be beneficial for electric vehicle manufacturers and individuals interested in electric vehicles. In this comparison, the performance of TF-IDF and FastText feature extraction in sentiment classification with SVM will be evaluated. SVM performance is assessed based on accuracy, precision, recall, and F1-score for each feature extraction technique used. The test results show an average accuracy above 83%, with the highest values being 86% for accuracy, 79% for precision, 52% for recall, and 58% for F1-score.  
COMPARATIVE SENTIMENT ANALYSIS OF VISITOR REVIEWS FOR WATERBOM BALI TOURIST ATTRACTION ON TRIPADVISOR SOCIAL MEDIA USING RANDOM FOREST AND NAÏVE BAYES CLASSIFICATION Hilmi, Hilmi Abdul Gani; Solihah, Binti; Sari, Syandra
Intelmatics Vol. 4 No. 2 (2024): Juli-Desember
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/v4i1.19278

Abstract

With the advancement of technology, especially the internet, the role of the internet as the primary source of information in global life is becoming increasingly crucial. This is particularly true in the context of searching for information about tourist destinations before visiting them. TripAdvisor is a website designed for searching travel destinations and attractions. On this platform, users can provide reviews and see comments from other travelers regarding various tourist destinations, including Waterbom Bali. To gain insights into visitors' perspectives and enhance services for them, the overwhelming number of reviews can be analyzed for sentiment to understand whether travelers' views tend to be positive, negative, or neutral. In this research, the Random Forest and Naïve Bayes methods are employed to conduct sentiment analysis. Scraping data from Waterbom Bali resulted in a dataset of 5750 entries. Despite data imbalance after labeling positive, negative, and neutral sentiments, class imbalance techniques will be applied. The sentiment analysis method, comparing Random Forest and Naïve Bayes, is implemented using the Word2Vec feature extraction method to evaluate its effectiveness. Experimental results show significant differences between the two methods. In Random Forest, after undersampling, an accuracy of 24% was obtained, while oversampling resulted in an accuracy of 98%. Meanwhile, for Multinomial Naïve Bayes, after undersampling, an accuracy of 36% was achieved, and oversampling yielded an accuracy of 97%.
Sentiment Analysis And Topic Modelling Of Candidate News In The 2024 General Election On Twitter Social Media Using Latent Dirichlet Allocation (LDA) Method Ramadhan, Syahrul; Siswanto, Teddy; Sari, Syandra
Intelmatics Vol. 5 No. 1 (2025): January-June
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/v5i1.21058

Abstract

The use of Twitter as a platform to express public opinion regarding fuel subsidies in Indonesia. Through sentiment analysis using Support Vector Machine method and word-based lexicon, this study reveals that the majority of people are in favour of fuel price increase or subsidy policy change. The sentiment data obtained from this research, which includes positive, neutral and negative sentiments, provides a clear picture of the public's views on the issue. SVM classification method and validation with K-Fold Cross Validation were used to ensure the accuracy of sentiment analysis results obtained from Twitter data. This research is also expected to help society to gauge public opinion on news and candidates in elections. It helps understand how people respond to certain political issues and candidates and the results of sentiment analysis and topic modelling can provide a better understanding of the key issues that matter to voters. This can help candidates and political parties to craft more effective campaign messages and can also be used to detect hoaxes or false information that may spread on social media during elections. This is important for maintaining the integrity of the election.
UI/UX Development for Tour Ticketing on Pari Island using User Centered Design Hudzafah, Abdullah; Pratiwi, Dian; Sari, Syandra
Intelmatics Vol. 5 No. 2 (2025): July-December
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/v5i2.21023

Abstract

UI/UX Development of UCD-Based Tourism Tour Ticketing on Pari Island, which currently feels like the method of ordering tourism services on Pari Island is still too conventional, especially in the tourism sector. In fact, purchasing tourism tour tickets with methods that follow technological developments greatly influences efficiency in handling the surge of tourists coming to Pari Island, especially on weekends and other holidays. On Pari Island, purchasing tickets for tourism such as homestays, catering, snorkeling equipment rentals, bicycles, and motorbikes is still considered conventional where tourists who come to Pari Island must look for homestays and book tickets directly on the spot, in this study an application was created with a simple and attractive ticket purchasing concept (E-Ticket) which aims to improve the UCD-based tourism tour ticket ordering system on Pari Island.