Presentation | 2018-09-06 Tag recommendation based on the relationship with user popularity on SNS Xueting Wang, Toshihiko Yamasaki, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In the content sharing service such as SNS, there are some scores which can express the degree of popularity, such as the number of views of images or videos. A high popularity score is expected by both general users and corporate promotion. In this paper, we propose a tag recommendation method to increase the popularity score.The proposed algorithm is based on PageRank, FolkRank and FolkPopularityRank (FP-Rank) algorithms.This algorithm not only uses co-occurrence between tags, but also considers the popularity degree of users and posted contents with these tags. Thus we can rank tags based on the influence on popularity.The proposed method learned with a total of 60,000 post images with tags from Flickr's public data sets and made tag recommendation with 2000 test data.In addition, we constructed a model that can predict the number of views by using tags and posted images as features. Using the prediction model, we evaluated the effect of increasing popularity of each method by adding recommended tags as features to compare the change in the number of predicted viewing numbers. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Social network service / tag recommendation / graph model |
Paper # | MVE2018-17 |
Date of Issue | 2018-08-30 (MVE) |
Conference Information | |
Committee | MVE |
---|---|
Conference Date | 2018/9/6(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Kenji Mase(Nagoya Univ.) |
Vice Chair | Masayuki Ihara(NTT) |
Secretary | Masayuki Ihara(NTT) |
Assistant | Satoshi Nishiguchi(Oosaka Inst. of Tech.) / Masanori Yokoyama(NTT) |
Paper Information | |
Registration To | Technical Committee on Media Experience and Virtual Environment |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Tag recommendation based on the relationship with user popularity on SNS |
Sub Title (in English) | |
Keyword(1) | Social network service |
Keyword(2) | tag recommendation |
Keyword(3) | graph model |
1st Author's Name | Xueting Wang |
1st Author's Affiliation | The University of Tokyo(UTokyo) |
2nd Author's Name | Toshihiko Yamasaki |
2nd Author's Affiliation | The University of Tokyo(UTokyo) |
Date | 2018-09-06 |
Paper # | MVE2018-17 |
Volume (vol) | vol.118 |
Number (no) | MVE-211 |
Page | pp.pp.25-30(MVE), |
#Pages | 6 |
Date of Issue | 2018-08-30 (MVE) |