| Presentation | 2021-07-02 Analysis on Geographic Bias in Private Graphs on Twitter towards SNS Marketing Applications Takeshi Sakaki, Shogo Matsuno, Yasuhiro Hino, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In marketing, consumers with high homogeneity have been regarded as a cluster, and the cluster has been used to target a group of consumers for marketing communication and advertising distribution. Before the Web, demographic attributes such as gender, region, age, and occupation were used as the attributes of highly homogeneous consumers. On the other hand, with the advent of the Web, consumers have begun to take actions based on units different from these attributes. With this background, targeting based on social graphs is said to be effective in SNS marketing. As a typical approach, there is a hypothesis that it is effective to treat a group of users connected by a private graph as a cluster. This is based on two characteristics of private graphs: 1) users connected by private graphs are highly homogeneous, and 2) information is easily transmitted among users connected by private graphs. However, there are few studies that have verified the existence of private graphs. In this study, we will verify whether private graphs actually exist. In particular, we focus on the private graphs of users who live close to each other. We verified that users who are connected in social graphs on Twittter are geographically biased. Based on this result, we explore the possibility of effective marketing communication and advertisement distribution by treating users who are grouped by geographic units as a cluster. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | marketing / web maining / information diffusion / social network analysis |
| Paper # | NLC2021-5 |
| Date of Issue | 2021-06-25 (NLC) |
| Conference Information | |
| Committee | NLC / IPSJ-ICS |
|---|---|
| Conference Date | 2021/7/2(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Application of natural language processing and intelligent systems, and general topic of NLP |
| Chair | Kazutaka Shimada(Kyushu Inst. of Tech.) |
| Vice Chair | Mitsuo Yoshida(Toyohashi Univ. of Tech.) / Takeshi Kobayakawa(NHK) |
| Secretary | Mitsuo Yoshida(Univ. of Tokyo) / Takeshi Kobayakawa(Hiroshima Univ. of Economics) |
| Assistant | Kanjin Takahashi(Sansan) / Ko Mitsuda(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Natural Language Understanding and Models of Communication / Special Interest Group on Intelligence and Complex Systems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Analysis on Geographic Bias in Private Graphs on Twitter towards SNS Marketing Applications |
| Sub Title (in English) | |
| Keyword(1) | marketing |
| Keyword(2) | web maining |
| Keyword(3) | information diffusion |
| Keyword(4) | social network analysis |
| 1st Author's Name | Takeshi Sakaki |
| 1st Author's Affiliation | Hottolink, inc.(Hottolink) |
| 2nd Author's Name | Shogo Matsuno |
| 2nd Author's Affiliation | Gunma University(Gunma Univ.) |
| 3rd Author's Name | Yasuhiro Hino |
| 3rd Author's Affiliation | Hottolink, inc.(Hottolink) |
| Date | 2021-07-02 |
| Paper # | NLC2021-5 |
| Volume (vol) | vol.121 |
| Number (no) | NLC-82 |
| Page | pp.pp.25-30(NLC), |
| #Pages | 6 |
| Date of Issue | 2021-06-25 (NLC) |