Çankaya GCRIS Standart veritabanının içerik oluşturulması ve kurulumu Research Ecosystems (https://www.researchecosystems.com) tarafından devam etmektedir. Bu süreçte gördüğünüz verilerde eksikler olabilir.

Yazılım Mühendisliği Bölümü Yayın Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/2147

Browse

Browsing Yazılım Mühendisliği Bölümü Yayın Koleksiyonu by Subject "Anonymous Document Pairs"

Filter results by typing the first few letters
Now showing 1 - 1 of 1
  • Thumbnail Image
    Article
    Citation Count: Canbay, Pelin; Sezer, Ebru; Sever, Hayri (2020). "Deep Combination of Stylometry Features in Forensic Authorship Analysis", International Journal of Information Security Science, Vol. 9, no. 3, pp. 154-163.
    Deep Combination of Stylometry Features in Forensic Authorship Analysis
    (2020) Canbay, Pelin; Sezer, Ebru; Sever, Hayri; 11916
    Authorship Analysis (AA) in forensic is a process aim to extract information about an author from his/her writings. Forensic AA is needed for detection characteristics of anonymous authors to make better the security of digital media users who are exposed to disturbing entries such as threats or harassment emails. To analyze whether two anonymous short texts were written by the same author, we propose a combination of stylometry features from different categories in different progress. In the majority of the previous AA studies, the stylometric features from different categories are concatenated in a preprocess. In these studies, during the learning process, no category-specific operations are performed; all categories used are evaluated equally. On the other hand, the proposed approach has a separate learning process for each feature category due to their qualitative and quantitative characteristics and combines these processes at the decision phase by using a Combination of Deep Neural Networks (C-DNN). To evaluate the Authorship Verification (AV) performance of the proposed approach, we designed and implemented a problem-specific Deep Neural Network (DNN) for each stylometry category we used. Experiments were conducted on two English public datasets. The results show that the proposed approach significantly improves the generalization ability and robustness of the solutions, and also have better accuracy than the single DNNs.