Social network user identification
Conference proceedings article
Authors/Editors
Strategic Research Themes
No matching items found.
Publication Details
Author list: Jamjuntra L., Chartsuwan P., Wonglimsamut P., Porkaew K., Supasitthimethee U.
Publisher: Hindawi
Publication year: 2017
Start page: 132
End page: 137
Number of pages: 6
ISBN: 9781467390774
ISSN: 0146-9428
eISSN: 1745-4557
Languages: English-Great Britain (EN-GB)
Abstract
Many people use more than one social network services (SNS). They create accounts for sharing both private and public information. These information are digital footprints that can be used to identify the owners. To identify the account identities, it is necessary to gather user information regarding their online behaviors. It can be used for marketing and customer interaction. In this paper, the architecture for matching accounts across multiple SNSs was proposed. It is designed for extensibility and configurability so that, given an account of a person on an SNS, it can be used to find other accounts belonging to the same person on any SNS. The system collects account information, such as username, friends, and interests from accounts on various SNSs and compare them using Jaro-Winkler distance algorithm. To be specific, this system focuses on finding Twitter accounts of a person given his/her Facebook account. An experiment of 138 user accounts are tested and its accuracy was 55%, which is almost twice better than a previous research on a similar situation. ฉ 2017 IEEE.
Keywords
footprint, identity resolution, identity search, user identification
Contact Information