Abstract | ||
---|---|---|
In social media websites, such as Twitter and Digg, certain content will attract much more visitors than others. Predicting which content will become popular is of interest to website owners and market analysts. In this paper, we present a novel technique to predict popularity using the connection features of individuals and their community. Our approach is based on the hypothesis that connection plays a dominant role in spreading content on social media. The resulting predictor is more efficient than approaches which estimate popularity by complex graph properties, and more accurate than approaches that use simple visit counts. We evaluated the proposed approach empirically on several real-life data sets. Results indicate that, compared with the conventional methods, our approach is both accurate and computationally efficient. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/ICC.2012.6364063 | ICC |
Keywords | Field | DocType |
digg,social networks,popularity prediction,connectivity-based popularity prediction approach,complex graph property,twitter,social media web sites,social media,market analysts,social networking (online),machine learning,real-life data sets,optimization,publishing,media,clustering algorithms,accuracy | World Wide Web,Social network,Social media,Graph property,Social media optimization,Computer science,Popularity | Conference |
ISSN | ISBN | Citations |
1550-3607 E-ISBN : 978-1-4577-2051-2 | 978-1-4577-2051-2 | 1 |
PageRank | References | Authors |
0.36 | 7 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Huangmao Quan | 1 | 10 | 0.87 |
Ana Milicic | 2 | 15 | 3.19 |
Slobodan Vucetic | 3 | 637 | 56.38 |
Jie Wu | 4 | 8307 | 592.07 |