Personalized News Recommendation System

Melis Özkara; Metin Turan

Article Details

Personalized News Recommendation System

Authors:

Melis Özkara | Metin Turan

Publisher:

Istanbul Ticaret University

Main Topics:

Bilgisayar Yazılımı

Journal:

İstanbul Ticaret Üniversitesi Teknoloji ve Uygulamalı Bilimler Dergisi Vol.5 Issue 2, pp.123-133

Document Type:

Article

Publication Date:

2/2023

Document Language:

English

Document ID (Org No.):

2001281283

pISSN:

2645-8969

Keywords:

Abstract:

 Recommendation Systems are the methods that suggest the next choices of the user in a predictable way, based on the preferences made by the user before. This method is become even more popular nowadays and it can be applied to any topic or field that needs future estimation evaluating the data at hand. It is a kind of information extraction study. Furthermore, the fact that Amazon receives about 35 of its revenue from referral systems is an indication of how important this method is. However, news recommendation system which is a similar application area, is not also widely used as others. In this study, it is aimed to design a news recommendation system by taking into account the sites the user enters, the words that they searched for and bookmarks. The machine learning model has been trained with a data set that includes news categories and news content in order to present the news to the user as interested. By giving the data from the user environment to the trained model, the found interested categories of the user is processed instantly by the RSS. These news selected from RSS are shown to the user in order of priority regarding the daily news agenda. The real user test showed impressive accuracy as 89. This solution presents a content-based recommendation system as nature of the problem.

 Recommendation Systems are the methods that suggest the next choices of the user in a predictable way, based on the preferences made by the user before. This method is become even more popular nowadays and it can be applied to any topic or field that needs future estimation evaluating the data at hand. It is a kind of information extraction study. Furthermore, the fact that Amazon receives about 35 of its revenue from referral systems is an indication of how important this method is. However, news recommendation system which is a similar application area, is not also widely used as others. In this study, it is aimed to design a news recommendation system by taking into account the sites the user enters, the words that they searched for and bookmarks. The machine learning model has been trained with a data set that includes news categories and news content in order to present the news to the user as interested. By giving the data from the user environment to the trained model, the found interested categories of the user is processed instantly by the RSS. These news selected from RSS are shown to the user in order of priority regarding the daily news agenda. The real user test showed impressive accuracy as 89. This solution presents a content-based recommendation system as nature of the problem.

 Recommendation Systems are the methods that suggest the next choices of the user in a predictable way, based on the preferences made by the user before. This method is become even more popular nowadays and it can be applied to any topic or field that needs future estimation evaluating the data at hand. It is a kind of information extraction study. Furthermore, the fact that Amazon receives about 35 of its revenue from referral systems is an indication of how important this method is. However, news recommendation system which is a similar application area, is not also widely used as others. In this study, it is aimed to design a news recommendation system by taking into account the sites the user enters, the words that they searched for and bookmarks. The machine learning model has been trained with a data set that includes news categories and news content in order to present the news to the user as interested. By giving the data from the user environment to the trained model, the found interested categories of the user is processed instantly by the RSS. These news selected from RSS are shown to the user in order of priority regarding the daily news agenda. The real user test showed impressive accuracy as 89. This solution presents a content-based recommendation system as nature of the problem.

 Öneri Sistemleri, kullanıcının daha önce yapmış olduğu tercihlere dayalı olarak, kullanıcının bir sonraki tercihlerini öngörülebilir bir şekilde öneren yöntemlerdir. Bu yöntem günümüzde daha da popüler hale gelmiştir ve eldeki verileri değerlendirerek geleceğe yönelik tahmin gerektiren herhangi bir konu veya alana uygulanabilir. Bir tür bilgi çıkarma çalışmasıdır. Ayrıca Amazonun gelirinin yaklaşık 35ini yönlendirme sistemlerinden elde etmesi bu yöntemin ne kadar önemli olduğunun bir göstergesidir. Ancak benzer bir uygulama alanı olan haber tavsiye sistemi de diğerleri kadar yaygın olarak kullanılmamaktadır. Bu çalışmada, kullanıcının girdiği siteler, aradığı kelimeler ve yer imleri dikkate alınarak bir haber öneri sistemi tasarlamak amaçlanmıştır. Haberleri kullanıcıya ilgili olarak sunabilmek için makine öğrenmesi modeli, haber kategorilerini ve haber içeriklerini içeren bir veri seti ile eğitilmiştir. Kullanıcı ortamından gelen veriler eğitilen modele verilerek, kullanıcının bulunan ilgili kategorileri RSS tarafından anlık olarak işlenir. RSSden seçilen bu haberler, günlük haber gündemine göre öncelik sırasına göre kullanıcıya gösterilir. Gerçek kullanıcı testi 89 gibi etkileyici bir doğruluk gösterdi. Bu çözüm, sorunun doğası gereği içerik tabanlı bir öneri sistemi sunar.

Article Details

Personalized News Recommendation System

Authors:

Melis Özkara | Metin Turan

Publisher:

Istanbul Ticaret University

Main Topics:

Bilgisayar Yazılımı

Journal:

İstanbul Ticaret Üniversitesi Teknoloji ve Uygulamalı Bilimler Dergisi Vol.5 Issue 2, pp.123-133

Document Type:

Article

Publication Date:

2/2023

Document Language:

English

Document ID (Org No.):

2001281283

pISSN:

2645-8969

Personalized News Recommendation System

Recommendation Systems

NLP

Machine Learning.

Kişisel Haber Tavsiye Sistemi

İçerik Tabanlı Tavsiye Sistemleri

NLP

Issues

Article Details

Authors: Melis Özkara | Metin Turan

Publisher: Istanbul Ticaret University

Main Topics: Bilgisayar Yazılımı

Journal: İstanbul Ticaret Üniversitesi Teknoloji ve Uygulamalı Bilimler Dergisi Vol.5 Issue 2, pp.123-133

Document Type: Article

Publication Date: 2/2023

Document Language: English

Document ID (Org No.): 2001281283

pISSN: 2645-8969

Issues

Authors:

Melis Özkara | Metin Turan

Publisher:

Istanbul Ticaret University

Main Topics:

Bilgisayar Yazılımı

Journal:

İstanbul Ticaret Üniversitesi Teknoloji ve Uygulamalı Bilimler Dergisi Vol.5 Issue 2, pp.123-133

Document Type:

Article

Publication Date:

2/2023

Document Language:

English

Document ID (Org No.):

2001281283

pISSN:

2645-8969