Sistem Rekomendasi Destinasi Wisata di Kota Surabaya Menggunakan Metode Content Based Filtering dan Neural Collaborative Filtering

Syakura, Zaky Izmi (2024) Sistem Rekomendasi Destinasi Wisata di Kota Surabaya Menggunakan Metode Content Based Filtering dan Neural Collaborative Filtering. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5003201148-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (2MB) | Request a copy

Abstract

Dalam menghadapi kesulitan akses informasi rekomendasi wisata di Kota Surabaya akibat melimpahnya informasi yang beragam terutama selama masa pandemi dan penurunan ekonomi global maka sektor pariwisata diidentifikasi sebagai opsi potensial untuk meningkatkan PDB, penerimaan devisa, dan penyerapan tenaga kerja. Meskipun destinasi pariwisata Kota Surabaya menawarkan kekayaan budaya dan alam yang menarik, promosi yang minim dan kurangnya informasi tentang daya tariknya menjadi kendala. Dengan menggunakan pendekatan neural collaborative filtering dan content based filtering pada penelitian ini bertujuan untuk menyusun sistem rekomendasi tempat wisata yang lebih personal dan relevan. Penelitian ini diharapkan dapat mengatasi kesulitan akses informasi dan meningkatkan kunjungan wisatawan dapat mendukung pengembangan pariwisata di tingkat daerah dan menyediakan informasi yang mudah diakses untuk wisatawan dan meningkatkan kunjungan wisatawan di Kota Surabaya. Content based filtering yang menganalisis fitur item berdasarkan nama, deskripsi, dan kategori tempat, menghasilkan nilai Root Mean Square Error (RMSE) 2,9310 dan nilai F-1 Score 0,7 atau 70%, tetapi memiliki kelemahan jika data pengguna tidak cukup. Sebaliknya, neural collaborative filtering menunjukkan performa lebih baik dengan nilai RMSE 1,4207 dan nilai F-1 Score 0,76 atau 76% yang menandakan hasil yang lebih baik. Neural collaborative filtering digunakan untuk memberikan rekomendasi destinasi wisata. Penelitian ini membuktikan bahwa neural collaborative filtering dapat meningkatkan kualitas rekomendasi dan mendukung pengembangan pariwisata.
=======================================================================================================
Faced with difficulties in accessing tourism recommendation information in Surabaya due to the overwhelming variety of information, especially during the pandemic and global economic downturn, the tourism sector has been identified as a potential option to boost GDP, foreign exchange earnings, and employment. Despite Surabaya's tourist destinations offering rich cultural and natural attractions, minimal promotion and lack of information about their appeal remain obstacles. This study aims to develop a more personal and relevant tourism recommendation system using neural collaborative filtering and content based filtering. The research is expected to address information access issues, increase tourist visits, support regional tourism development, and provide easily accessible information for tourists, thereby boosting tourism in Surabaya. Content based filtering, which analyzes item features based on name, description, and category, produced a Root Mean Square Error (RMSE) of 2.9310 and F1-Score 0.70 or 70%, but has limitations if user data is insufficient. Conversely, neural collaborative filtering shows better performance with an RMSE of 1.4207 and F1-Score 0.76 or 76%, indicating better results. Neural collaborative filtering is used to recommend tourist destinations. This research demonstrates that neural collaborative filtering can enhance the quality of recommendations and support tourism development.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	recommendation system, content based filtering, neural collaborative filtering, surabaya, tourists, sistem rekomendasi, content based filtering, neural collaborative filtering, surabaya, wisatawan.
Subjects:	Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) Q Science > QA Mathematics > QA76.9.I58 Recommender systems (Information filtering)
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Zaky Izmi Syakura
Date Deposited:	09 Aug 2024 03:03
Last Modified:	09 Aug 2024 03:03
URI:	http://repository.its.ac.id/id/eprint/114885

Actions (login required)

View Item