CIVILICA We Respect the Science
(ناشر تخصصی کنفرانسهای کشور / شماره مجوز انتشارات از وزارت فرهنگ و ارشاد اسلامی: ۸۹۷۱)

Authorship Attribution in Persian Scripts Using Neural Networks

عنوان مقاله: Authorship Attribution in Persian Scripts Using Neural Networks
شناسه ملی مقاله: ACCSI12_175
منتشر شده در دوازدهمین کنفرانس سالانه انجمن کامپیوتر ایران در سال 1385
مشخصات نویسندگان مقاله:

Afshin Rahimi - Web Intelligence Laboratory , Department of Computer Engineering , Sharif University of Technology , Tehran, Iran
Hassan Abolhassani - Department of Computer Engineering , Faculty of Computer Engineering Sharif University of Technology, Tehran,Iran
Kyumars Sheykh Esmaili - Web Intelligence Laboratory , Department of Computer Engineering , Sharif University of Technology , Tehran, Iran

خلاصه مقاله:
Authorship Attribution is an interesting problem with many applications like Fraud detection, email classification , deciding the authorship of famous documents like the bible, attributing authors to pieces of texts in collaborative writing, and software forensics. Authorship attribution attempts to recognize authors of different scripts based on their writing style. In this paper, four parsian bloggers have been selected and then using their writing style and features, we have tried to apply a neural network based solution for authorship attribution problem among them. A couple of experiments have been designed for evaluating performance of this neural network and results are reported.

کلمات کلیدی:
authorship Attribution , Stylometery , Neural Network , Persian Scripts

صفحه اختصاصی مقاله و دریافت فایل کامل: https://civilica.com/doc/44561/