M.Sc. Tezi Görüntüleme | |||||||||||||||||||||
|
|
||||||||||||||||||||
| Summary: Nowadays, chat mediums take an important place at social and daily life of humans. Conversations in chat mediums are taken shape with many factors such as chatters sex, habits, tendencies and etc. Because chat mediums are used as a communication and information-sharing tool, the medium may include important information about chatters. Therefore, extraction of information from chat mediums is getting important more and more. Owing to information extraction, valuable information about chatters can be obtained from the mediums. A part of this, a sex discrimination function is also proposed for sex identification of chatter in the medium. To develop the identification system, statistical information is acquired from a specially designed chat system at a local network and Internet (mIRC). By the help of this statistical information, the sex discrimination function is formed. Hence, conversations from the mediums are subjected by the function and sexes of chatters are defined. Then, the results are compared with the real data and the accuracy of the identification system is evaluated. Key Words: Natural Language Processing, Turkish Based Dialog Systems, Chat Engine Design, Information Extraction, Sex Identification, Knowledge Representation, Semantic Analysis | |||||||||||||||||||||