Social network user identification

Conference proceedings article

ผู้เขียน/บรรณาธิการ

กลุ่มสาขาการวิจัยเชิงกลยุทธ์

ไม่พบข้อมูลที่เกี่ยวข้อง

รายละเอียดสำหรับงานพิมพ์

รายชื่อผู้แต่ง: Jamjuntra L., Chartsuwan P., Wonglimsamut P., Porkaew K., Supasitthimethee U.

ผู้เผยแพร่: Hindawi

ปีที่เผยแพร่ (ค.ศ.): 2017

หน้าแรก: 132

หน้าสุดท้าย: 137

จำนวนหน้า: 6

ISBN: 9781467390774

นอก: 0146-9428

eISSN: 1745-4557

URL: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85017499161&doi=10.1109%2fKST.2017.7886120&partnerID=40&md5=86f5b789979ad0d651c5edd1cccbac1d

ภาษา: English-Great Britain (EN-GB)

ดูบนเว็บไซต์ของสำนักพิมพ์

บทคัดย่อ

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.

คำสำคัญ

footprint, identity resolution, identity search, user identification