Product Aspect Detection in Customer Complaints by Using Latent Dirichlet Allocation

ATICI B., Omurca S., Ekinci E.

2017 International Conference on Computer Science and Engineering (UBMK), Antalya, Türkiye, 5 - 08 Ekim 2017, ss.250-254 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/ubmk.2017.8093384
  • Basıldığı Şehir: Antalya
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.250-254
  • Anahtar Kelimeler: collapsed gibbs sampling, latent dirichlet allocation, aspect extraction
  • Kocaeli Üniversitesi Adresli: Evet

Özet

Nowadays, people take into account complaints of customers about products or services before purchasing them. However, inconsistency as a result of information pollution on the internet make it difficult to get reliable information for users. In terms of companies, they spend a great deal of time and human resource to read complaints one by one. So, it is very important to address the focus of customers' complaints about the companies for managing relation between customers and companies. In this study, it is aimed to determine complaints and dissatisfactions about products, services or companies from the complaints in the website "www.sikayetvar.com" by using LDA (Latent Dirichlet Allocation).