Powered by OpenAIRE graph
Found an issue? Give us feedback
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Classification of Customer Complaints Using BERTopic Topic Modelling Technique

Authors: KORUYAN, Kutan;

Classification of Customer Complaints Using BERTopic Topic Modelling Technique

Abstract

Müşteri şikâyetlerinin analizi işletmeler açısından geçmişte yaptıkları hataları düzeltme, marka değerini koruma ve yeni müşteriler edinmeleri açısından önemli bir kavramdır. Özellikle şikâyet verisinin büyüklüğü arttıkça verinin sınıflandırılması ve tahminlenmesi için makine öğrenmesi tekniklerinden yararlanmak zaman ve maliyet açısından karar vericilere avantaj sağlamaktadır. Bu yüzden çalışmada, müşteri şikayetlerinin ürün bazında ve genel anlamda hangi farklı konularda dağılım gösterdiğinin bulunması amacıyla güncel bir yaklaşım olan BERTopic konu modelleme tekniğinden yararlanılmıştır. Buna yönelik olarak da veri seti olarak 2020 yılına ait bir tüketici elektroniği perakende şirketine yapılan şikayetler kullanılmış ve sınıflandırılmıştır. Bunun yanında, şikayetlerin aylık olarak zaman içindeki değişimi de dinamik konu modelleme kullanılarak incelenmiştir. Sonuçlara göre en fazla şikâyet kargolama, televizyon, cep telefonu, dizüstü bilgisayar, kulaklık, tablet, mağaza çalışanları, sipariş iptali konularında yoğunlaşmıştır.

The analysis of customer complaints enables companies to amend mistakes, protect brand value and attract new customers. Utilizing machine learning techniques for data classification and prediction provide decision makers with time and cost benefits, particularly with increased complaint data size. Therefore, this study employed BERTopic topic modelling technique, a contemporary approach, to examine customer complaint distribution with respect to distinct topics, by product and in general. In the study, the complaints submitted to a consumer electronics retailer in 2020 were adopted and classified. The monthly variation of the complaints was also investigated with dynamic topic modelling. The results showed that the complaints concentrated more heavily on shipping, television, mobile phone, laptop, earphones, tablets, store clerks and order cancellation topics.

Keywords

Müşteri Şikayetleri;Konu Modelleme;BERTopic;Dinamik Konu Modelleme, Customer Complaints;Topic Modelling;BERTopic;Dynamic Topic Modelling

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!