| Presentation | 2016-07-16 Analysis and Prediction of Popularity Dynamics of User Generated Contents Tatsuya Tanaka, Shingo Ata, Masayuki Murata, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In recent years, social networking services such as YouTube, which share UGC (User Generated Contents) have become much attracted. An efficient control of UGC is one of important role to achieve an optimized placement of advertisements for end users, and/or content-aware caching control for improve the utilization of network resources. To this end, it is effective to forecast the future popularity of the content as early as possible, so that we can take a proactive action to highly popular contents. In this paper, we propose a method to classify time dependent variations of popularity (popularity patterns) of UGCs by using k-means clustering, and analyze tendencies led by popularity patterns. We then propose a method to identify UGCs which are expected to be popular in future, by taking both the initial part of popularity patterns and actual counts of downloads into consideration. Our experimental results show that the accuracy of identification of popular UGCs can be increased around 10% by considering the initial part of popularity patterns. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | YouTube / popularity prediction / view count transition pattern / k-means / Naive Bayes Classifier |
| Paper # | IN2016-31 |
| Date of Issue | 2016-07-08 (IN) |
| Conference Information | |
| Committee | IN |
|---|---|
| Conference Date | 2016/7/15(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Matsumaecho Sougo Center |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Next Generation/New Generation/Future Network, Cloud/Data Center Network, SDN (Open Flow etc.), NFV, IPv6, Overlay Network, P2P, Content Distribution, Content Exchange, TCP/IP, BGP, DNS, HTTP/2, Routing, Switching, Traffic Engineering, etc. |
| Chair | Katsunori Yamaoka(Tokyo Inst. of Tech.) |
| Vice Chair | Takuji Kishida(NTT) |
| Secretary | Takuji Kishida(KDDI R&D Labs.) |
| Assistant | Kunitake Kaneko(Keio Univ.) / Takashi Natsume(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Information Networks |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Analysis and Prediction of Popularity Dynamics of User Generated Contents |
| Sub Title (in English) | |
| Keyword(1) | YouTube |
| Keyword(2) | popularity prediction |
| Keyword(3) | view count transition pattern |
| Keyword(4) | k-means |
| Keyword(5) | Naive Bayes Classifier |
| 1st Author's Name | Tatsuya Tanaka |
| 1st Author's Affiliation | Osaka University(Osaka Univ.) |
| 2nd Author's Name | Shingo Ata |
| 2nd Author's Affiliation | Osaka City University(Osaka City Univ.) |
| 3rd Author's Name | Masayuki Murata |
| 3rd Author's Affiliation | Osaka University(Osaka Univ.) |
| Date | 2016-07-16 |
| Paper # | IN2016-31 |
| Volume (vol) | vol.116 |
| Number (no) | IN-137 |
| Page | pp.pp.49-54(IN), |
| #Pages | 6 |
| Date of Issue | 2016-07-08 (IN) |