Influence maximization for viral marketing in online social networks
In this project, various seeds selection algorithms are implemented to select most influential individuals from social networks. The selected individuals are expected to spread out desired marketing message to highest number of receivers through their connections in a social media marketing campaign...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/74045 |
| Summary: | In this project, various seeds selection algorithms are implemented to select most influential individuals from social networks. The selected individuals are expected to spread out desired marketing message to highest number of receivers through their connections in a social media marketing campaign. The process of information diffusion is simulated by independent cascade model and linear threshold model. A software tool is developed as a graphical interface to facilitate the entire process from taking user input to displaying important outputs from programs. The performance of various seed selection algorithms is evaluated based on the expected influence spread of selected seed nodes and time to complete selection. It was concluded that for social networks with low propagation probability, degree discount algorithm is most suitable, whereas for networks with high propagation probability, single discount selection should be applied. Future improvements of this project include implementation of weighted cascade diffusion model and other seed selection algorithms. |
|---|