Short Paper: User Identification across Online Social Networks Based on Similarities among Distributions of Friends’ Locations
| Autor: | Keisuke Ikeda, Masahiro Tani, Kojima Kazufumi |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
021110 strategic
defence & security studies Information retrieval Social network Basis (linear algebra) Computer science business.industry Short paper 0211 other engineering and technologies Contrast (statistics) 02 engineering and technology Identification (information) Similarity (network science) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Social media business |
| Zdroj: | IEEE BigData |
| Popis: | This paper describes a user identification method conducted across online social networks (OSNs) using information regarding friends’ locations, in contrast to a conventional method based on the similarity of two display names. This latter method encounters the problem of decreased identification accuracy if a user registers different display names across OSNs. Our proposed method aims at addressing this issue by utilizing information on friends’ locations. We convert location information extracted from an OSN to that of such geographic administrative units as country, state and city, and calculate the weighted occurrence frequency of a location pair on the basis of distance between the pair. This is based on the hypothesis that a friend list relatively rarely includes an account pair whose locations are extremely distant from one another. We calculate a similarity score between two accounts’ weighted occurrence frequencies for each geographic administrative unit. Finally, we identify a user on the basis of individual similarity scores or weighted average scores for a given geographic administrative unit. Evaluation experiments show that our proposed method improves performance over that of a conventional method (accuracy: 83.1%$\rightarrow$91.2%). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|