In this study; It is aimed to classify all kinds of notifications from customers in the banking sector, then prioritize these classes and give feedback to the customer according to this priority. In this way, it is aimed to produce quick solutions for priority notifications that will ensure customer satisfaction. In the literature review on the classification of data, high accuracy values; It has been observed that it is obtained by Logistic Regression, Long Short Term Memory (LSTM), Multinominal Naive Bayes and Support Vector Machine (SVM) algorithms. For this reason, training and testing processes were carried out using Natural Language Processing (NLP) methods on a real bank data set with these algorithms. With the two-stage approach presented as a new method, it has been achieved to increase the accuracy values above seventy percent by working with a limited number of data sets.
Natural Language Processing Machine Learning Turkish Text Classification Customer Satisfaction Logistic Regression Support Vector Machine Long Short Term Memory Multinominal Naive Bayes
Bu çalışmada; bankacılık sektöründe müşterilerden gelen her türlü bildirimlerin sınıflandırılması, sonrasında bu sınıfların önceliklendirilmesi ve bu önceliğe göre müşteriye geri bildirim verilmesi amaçlanmıştır. Bu sayede müşteri memnuniyeti sağlayacak öncelikli bildirimlere hızlı çözüm üretilebilmesi hedeflenmiştir. Verilerin sınıflandırılmasıyla ilgili yapılan literatür taramasında yüksek doğruluk değerlerinin; Lojistik Regresyon, Uzun Kısa Süreli Bellek, Multinominal Naive Bayes ve Destek Vektör Makinesi algoritmaları ile elde edildiği gözlemlenmiştir. Bu sebeple bu algoritmalarla gerçek bir banka veri seti üzerinde Doğal Dil İşleme (Natural Language Processing - NLP) yöntemleri kullanılarak eğitim ve sınama işlemleri gerçekleştirilmiştir. Yeni bir yöntem olarak sunulan iki aşamalı yaklaşımla sınırlı sayıda veri setiyle çalışılarak doğruluk değerlerini yüzde yetmişin üzerine çıkarılması başarılmıştır.
Doğal Dil İşleme Makine Öğrenimi Türkçe Metin Sınıflandırma Müşteri Memnuniyeti Logistic Regresyon Destek Vektör Makinesi Uzun Kısa Süreli Hafıza Multinominal Naive Bayes
Primary Language | Turkish |
---|---|
Subjects | Engineering |
Journal Section | Makaleler(Araştırma) |
Authors | |
Early Pub Date | June 29, 2023 |
Publication Date | June 29, 2023 |
Published in Issue | Year 2023 Volume: 16 Issue: 1 |
Article Acceptance
Use user registration/login to upload articles online.
The acceptance process of the articles sent to the journal consists of the following stages:
1. Each submitted article is sent to at least two referees at the first stage.
2. Referee appointments are made by the journal editors. There are approximately 200 referees in the referee pool of the journal and these referees are classified according to their areas of interest. Each referee is sent an article on the subject he is interested in. The selection of the arbitrator is done in a way that does not cause any conflict of interest.
3. In the articles sent to the referees, the names of the authors are closed.
4. Referees are explained how to evaluate an article and are asked to fill in the evaluation form shown below.
5. The articles in which two referees give positive opinion are subjected to similarity review by the editors. The similarity in the articles is expected to be less than 25%.
6. A paper that has passed all stages is reviewed by the editor in terms of language and presentation, and necessary corrections and improvements are made. If necessary, the authors are notified of the situation.
. This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.