Abstract—Managing customer feedback data has become a
necessity for firms in order for them to gain competitive
advantage in the sector. Analyzing customer complaints’ data to
find useful information that’s hidden is an important step in
understanding customers. This important, hidden knowledge
must be extracted automatically to allow firms to gain a better
understanding of the general market and of their own and their
competitors' customers. A firm can learn the needs of customers
and show how its products and services satisfy these needs by
analyzing these documents.
The aim of this research is to summarize and extract data
from unstructured customer feedback documents which are
about ignoring subscriptions to a telecommunication firm in
Turkey. The data are transformed to a collection of documents
by generating a document for each record. Text processing
techniques are applied. Cosine similarity analysis is used to
classify documents into relevant categories. Clusters are
determined.
Index Terms—Data mining, text mining, customer feedback
data, natural language processing.
E. Kahya-Özyirmidokuz is with the Computer Technologies Department,
Erciyes University, Kayseri, Turkey (e-mail: esrakahya@erciyes.edu.tr).
E. A. Stoica is with the Department of Information Economics, Lucian
Blaga University, Sibiu, Romania (e-mail: eduard.stoica@ulbsibiu.ro).
[PDF]
Cite: Eduard Alexandru Stoica and Esra Kahya Özyirmidokuz, "Mining Customer Feedback Documents," International Journal of Knowledge Engineering vol. 1, no. 1, pp. 68-71, 2015.
