Name
Abstract | ||
|---|---|---|
Retweeting is the key mechanism of information diffusion on microblogging community. It is very challenging for user to choose the suitable tweets for retweeting, given the diverse and massive messages received and limited time on site. Therefore, it is crucial to design a recommender system that automatically recommends tweets for user to retweet. Recommending tweets for retweeting is different from conventional recommender system due to limited explicit feedback, high proportion of cold-start tweets and short tweet active time. In this paper, we propose a novel retweet recommendation (RTR) framework which leverages the implicit feedback to help user find the potential tweets he may want to retweet. RTR is divided into offline learning and online recommendation so that tweets can be taken into account as soon as it is published. In offline learning, we adapt a matrix factorization method based on BPR-OPT framework with implicit feedback to compensate the limited explicit feedback. RTR is able to recommend cold-start tweet based on its content. Extensive experiments on real-world microblogging community clearly show that RTR outperforms upon existing methods. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1145/2390131.2390140 | DUBMMSM |
Keywords | DocType | Citations |
microblogging community,limited explicit feedback,limited time,offline learning,recommending tweet,cold-start tweet,implicit feedback,bpr-opt framework,conventional recommender system,novel retweet recommendation,cold start,microblogs | Conference | 7 |
PageRank | References | Authors |
0.56 | 6 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sheng Wang | 1 | 49 | 8.26 |
| Xiaobo Zhou | 2 | 7 | 0.56 |
| Ziqi Wang | 3 | 47 | 4.63 |
| Ming Zhang | 4 | 1963 | 107.42 |