uu.seUppsala University Publications
Change search
ReferencesLink to record
Permanent link

Direct link
Predicting Satisfaction in Customer Support Chat: Opinion Mining as a Binary Classification Problem
Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Languages, Department of Linguistics and Philology.
2016 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

The study explores binary classification with Support Vector Machines as means to predict a satisfaction score based on customer surveys in the customer supportdomain. Standard feature selection methods and their impact on results are evaluated and a feature scoring metric Log Odds Ratio is implemented for addressingasymmetrical class distributions. Results show that the feature selection andscoring methods implemented improve performance significantly. Results alsoshow that it is possible to get decent predictive values on test data based onlimited amount of training observations. However mixed results are presentedin a real-world application example as a there is a significant error rate fordiscriminating the minority class. We also show the negative effects of usingcommon metrics such as accuracy and f-measure for optimizing models whendealing with high-skew data in a classification context.

Place, publisher, year, edition, pages
2016. , 34 p.
Keyword [en]
Binary Classification, Customer Support, Chat, Opinion Mining, Support Vector Machines
National Category
Other Engineering and Technologies not elsewhere specified
URN: urn:nbn:se:uu:diva-300165OAI: oai:DiVA.org:uu-300165DiVA: diva2:950933
Educational program
Bachelor Programme in Language Technology
Available from: 2016-08-21 Created: 2016-08-03 Last updated: 2016-08-21Bibliographically approved

Open Access in DiVA

fulltext(448 kB)40 downloads
File information
File name FULLTEXT01.pdfFile size 448 kBChecksum SHA-512
Type fulltextMimetype application/pdf

By organisation
Department of Linguistics and Philology
Other Engineering and Technologies not elsewhere specified

Search outside of DiVA

GoogleGoogle Scholar
Total: 40 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 362 hits
ReferencesLink to record
Permanent link

Direct link