Author identification of newspaper columns using style and semantic features
Is this your thesis?
This record came from a bulk archive import. If it’s yours, link it to your profile.
Abstract (EN)
This study has two major purposes : To implement and compare the author classification results of different Naive Bayes Classifiers, and to investigate whether merging individual methods will increase classification success or not. The subjects of this study were newspaper columnists. Data was collected from well known public newspapers. This study first investigates Numeric, Nominal, Multinominal NBC, and their various merged versions. We then address each method using cross-validation. The results of the experiments show that merging multiple classification methods can increase classification success. Additionally, it depends on how well individual classification models are constructed.
Author
Ergin Doğan Yıldız
Institution
How to Cite
Ergin Doğan Yıldız (Master Thesis). Author identification of newspaper columns using style and semantic features, 2016, Feyziye Schools Foundation Işık University.
Keywords
License
Tüm Hakları Saklıdır
This work is shared under the specified license terms.
More theses from Feyziye Schools Foundation Işık University
- Examining the role of psychological well-being and sexual satisfaction in predicting marital adjustment(2021)
- Relations of 1994 and 2000 crises and their effects in Turkish capital markets(2002)
- Design of reed-solomon and convolutional coded OFDM system and performance analysis(2003)
- Evaluation of innovativeness of Turkey with respect to european union integration(2003)
- Project workspace: A computer supported collorative work tool for software project development(2005)
- Performance analysis of static agent architecture with centralized matchmaking(2005)
