SALAM, RIFQI IQBAL (2021) REKOMENDASI KONSULTAN HUKUM BERBASIS WEB DENGAN METODE CONTENT BASED FILTERING. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 Cover.pdf Download (1MB) | Preview |
|
Text (BAB I)
02 Bab 1.pdf Restricted to Registered users only Download (36kB) |
||
Text (BAB II)
03 Bab 2.pdf Restricted to Registered users only Download (271kB) |
||
Text (BAB III)
04 Bab 3.pdf Restricted to Registered users only Download (40kB) |
||
Text (BAB IV)
05 Bab 4.pdf Restricted to Registered users only Download (91kB) |
||
Text (BAB V)
06 Bab 5.pdf Restricted to Registered users only Download (32kB) |
||
Text (BAB VI)
07 Bab 6.pdf Restricted to Registered users only Download (76kB) |
Abstract
The recommendation system is one of the methods used to provide recommendations or item choices to the user. We often encounter recommendation systems in e-commerce to recommend other related products to buyers. In this study, the authors tried to implement a recommendation system with the Contentbased Filtering method in designing a web-based legal consultant application. This application recommends legal consultants whose profiles of areas of expertise are similar and in accordance with user problems. Recommendations are generated from calculations using the TF-IDF (Term Frequency Inverse Document Frequency) method and Cosine Similarity where the problem keywords entered by the user will be weighted values and their similarity is calculated with all legal consultant expertise profile document data in the database. After that, the value from the similarity calculation results is ranked and displayed as the recommendation. In the performance test, the average recommendation accuracy is 84%. Key words: Recommendation System, Content Based Filtering, Legal Consultant Sistem rekomendasi atau recommender system adalah salah satu metode yang digunakan untuk memberikan rekomendasi atau pilihan item kepada user. Sistem rekomendasi sering kita temui pada e-commerce untuk merekomendasikan produk lainnya yang terkait kepada pembeli. Pada penelitian ini penulis mencoba menerapkan sistem rekomendasi dengan metode Content-based Filtering pada perancangan aplikasi konsultan hukum berbasis web. Aplikasi ini merekomendasikan konsultan hukum yang profil bidang keahliannya mirip dan sesuai dengan permasalahan user. Rekomendasi dihasilkan dari penghitungan menggunakan metode TF-IDF (Term Frequency Inverse Document Frequency) dan Cosine Similarity dimana keyword masalah yang diinputkan user akan dilakukan pembobotan nilai dan dihitung kemiripannya dengan seluruh data dokumen profil keahlian konsultan hukum dalam database. Setelah itu, nilai dari hasil perhitungan kemiripan diranking dan ditampilkan menjadi hasil rekomendasi. Dalam uji performasi didapat keakuratan rekomendasi rata-rata sebesar 84%. Kata kunci: Sistem Rekomendasi, Content Based Filtering, Konsultan Hukum
Actions (login required)
View Item |