Loading...
- Type of Document: M.Sc. Thesis
- Language: English
- Document No: 39272 (52)
- University: Sharif University of Technology, International Campus, Kish Island
- Department: Science and Engineering
- Advisor(s): Sadighi Moshkenani, Mohsen
- Abstract:
- Networked computers are expanding more and more around the world, and digital social networks becoming of great importance for many people's work and leisure. Emails, Weblogs and Instant Messengers are popular instances of social networks. In this thesis, the main target is to have an advertisement according to user favorites and interests by mining his/her interactions in digital social networks. Briefly, in our method social network users are categorized based on the topics exchanges between them in the network, these topics discovered by mining of flowing data in that environment, considering that these topics shows the user willing, finally relevant advertisements will be represented to them. In fact, by finding people that have more chance to accept the desired advertisement, system will have more success rather than traditional method at lowered cost. To evaluate proposed method, our personal email archive was used. The results showed that this model can determine the subjects of messages with 78.4 percent accuracy. So, with the same accuracy, relevant advertisements can be presented to users. In addition, our proposed model in compare with other model showed that is more suitable for the targets of this project
- Keywords:
- Data Mining ; Social Networks ; Web Mining ; Social Media
- محتواي پايان نامه
- view