Garuda - Garba Rujukan Digital

Analysis of Public Sentiment Towards the Use of AI in Monitoring Waste via the SEMAR Monitoring Web and Its Impact on Flood Management in Semarang City Priskila Dwi Nilam Sari; Yohana Tri Widayati; Satrio Agung Prakoso
Jurnal Teknologi Informatika dan Komputer Vol. 11 No. 2 (2025): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v11i2.2838

Waste management and flood mitigation are key challenges in Semarang City. The Semarang City Government, through the Department of Communication and Informatics (Diskominfo), implemented the AI-based Pantau Semar web system to automatically detect waste accumulation and water puddles via a CCTV network. This study examines public sentiment toward the system, particularly from social media comments, and develops a sentiment classification model using IndoBERT. A quantitative approach with Natural Language Processing (NLP)-based sentiment analysis was applied. A total of 430 public comments from social media were classified into positive, negative, and neutral sentiments, and analyzed using a fine-tuned IndoBERT model. Results show that negative sentiment dominates (54%), followed by positive (30%) and neutral (16%). The model achieved 81% accuracy, with the highest F1-score in the negative class (0.89). These findings indicate that the public remains critical of the system’s performance, especially regarding waste accumulation and flooding, while also highlighting AI’s potential in environmental management and public opinion detection. The results provide a basis for developing more adaptive monitoring systems and improving government communication strategies to better address community needs.

Analysis of Boarding House Payment Patterns Using Data Visualization Techniques to Identify Delay Factors Abid Sakti Pamungkas; Yohana Tri Widayati; Harries Arizonia Ismail
Jurnal Teknologi Informatika dan Komputer Vol. 11 No. 2 (2025): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v11i2.2841

In an increasingly competitive business environment, the ability of Micro, Small, and Medium Enterprises (MSMEs) to survive heavily depends on effective cash flow management. Boarding house businesses, as a form of MSMEs in the service sector, face crucial challenges due to late rental payments by tenants. Management practices that are often reactive and intuitive have proven less effective in identifying the root causes of such issues. This study aims to apply an analytical approach using data visualization techniques to analyze rental payment patterns at Kost Green, Semarang. The main objective is to discover significant temporal patterns and identify tenant profile factors that strongly correlate with late payment behavior. The methodology employed is exploratory data analysis with a quantitative and visual approach, using primary data in the form of historical rental payment transactions over a one-year period, covering attributes such as tenant status and room type. The analysis process begins with a data preprocessing stage, in which a key analytical feature, Days_Late, is engineered to measure the duration of delays. The analysis is conducted using the Python programming language supported by the Pandas, Matplotlib, and Seaborn libraries. The findings reveal the existence of high-risk tenant segments (students) and critical time periods (certain months of the year) when delays tend to increase. The outcome of this research is a visual analytical report that provides a strong foundation for Kost Green management to make data-driven decisions, design more proactive and segmented billing strategies, and ultimately improve payment discipline and maintain healthy business cash flow.

Implementasi Sistem Informasi Media Promosi Pada Semesta Resto Berbasis Website Rudi Efendi, Muhammad; Yohana Tri Widayati; Satrio Agung Prakoso
Economic Reviews Journal Vol. 4 No. 4 (2025): Economic Reviews Journal
Publisher : Masyarakat Ekonomi Syariah Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56709/mrj.v4i4.903

This study focuses on the design and implementation of a web-based promotional media information system for Semesta Resto, a culinary business. The aim is to enhance the restaurant's operational efficiency and promotional effectiveness through a responsive website that offers interactive menus, online reservations, and real-time promotional updates. The research highlights the growing importance of digital media in the culinary industry, where consumer behavior is shifting towards online platforms. The study employs a qualitative descriptive approach, utilizing a case study methodology, and applies the Prototyping method in the development of the system. The findings demonstrate that the proposed system is expected to improve customer engagement, streamline operations, and increase revenue through better promotional strategies and easier customer interaction.

Analysis of Public Sentiment Towards the Use of AI in Monitoring Waste via the SEMAR Monitoring Web and Its Impact on Flood Management in Semarang City Priskila Dwi Nilam Sari; Yohana Tri Widayati; Satrio Agung Prakoso
Jurnal Teknologi Informatika dan Komputer Vol. 11 No. 2 (2025): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v11i2.2838

Waste management and flood mitigation are key challenges in Semarang City. The Semarang City Government, through the Department of Communication and Informatics (Diskominfo), implemented the AI-based Pantau Semar web system to automatically detect waste accumulation and water puddles via a CCTV network. This study examines public sentiment toward the system, particularly from social media comments, and develops a sentiment classification model using IndoBERT. A quantitative approach with Natural Language Processing (NLP)-based sentiment analysis was applied. A total of 430 public comments from social media were classified into positive, negative, and neutral sentiments, and analyzed using a fine-tuned IndoBERT model. Results show that negative sentiment dominates (54%), followed by positive (30%) and neutral (16%). The model achieved 81% accuracy, with the highest F1-score in the negative class (0.89). These findings indicate that the public remains critical of the system’s performance, especially regarding waste accumulation and flooding, while also highlighting AI’s potential in environmental management and public opinion detection. The results provide a basis for developing more adaptive monitoring systems and improving government communication strategies to better address community needs.

Analysis of Boarding House Payment Patterns Using Data Visualization Techniques to Identify Delay Factors Abid Sakti Pamungkas; Yohana Tri Widayati; Harries Arizonia Ismail
Jurnal Teknologi Informatika dan Komputer Vol. 11 No. 2 (2025): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v11i2.2841

In an increasingly competitive business environment, the ability of Micro, Small, and Medium Enterprises (MSMEs) to survive heavily depends on effective cash flow management. Boarding house businesses, as a form of MSMEs in the service sector, face crucial challenges due to late rental payments by tenants. Management practices that are often reactive and intuitive have proven less effective in identifying the root causes of such issues. This study aims to apply an analytical approach using data visualization techniques to analyze rental payment patterns at Kost Green, Semarang. The main objective is to discover significant temporal patterns and identify tenant profile factors that strongly correlate with late payment behavior. The methodology employed is exploratory data analysis with a quantitative and visual approach, using primary data in the form of historical rental payment transactions over a one-year period, covering attributes such as tenant status and room type. The analysis process begins with a data preprocessing stage, in which a key analytical feature, Days_Late, is engineered to measure the duration of delays. The analysis is conducted using the Python programming language supported by the Pandas, Matplotlib, and Seaborn libraries. The findings reveal the existence of high-risk tenant segments (students) and critical time periods (certain months of the year) when delays tend to increase. The outcome of this research is a visual analytical report that provides a strong foundation for Kost Green management to make data-driven decisions, design more proactive and segmented billing strategies, and ultimately improve payment discipline and maintain healthy business cash flow.

Title

Found 5 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 5 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 5 Documents
Search