User Identification Based on Display Names Across Online Social Networks
Authors:
Open Access
- 25 August 2017
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 5, 17342-17353
Abstract
User identification is very helpful for building a better profile of a user. Some works have been devoted to this issue. However, the existing works with a good performance are mainly based on the rich online data and do not consider the cost of online data acquisition. In this paper, we aim to address this issue with a lower cost of data acquisition. A machine learning-based solution is proposed solely based on the user’s display names. It consists of three key steps: we first analyze the users’ unique naming patterns that lead to information redundancies across sites; second, we construct features that exploit information redundancies; afterward, we employ machine learning method for user identification. The experiment shows that the proposed solution can provide excellent performance with F1 score reaching 96.24%, 92.49%, and 90.68% on three real different data sets, respectively. This paper shows the possibility of user identification with a lower cost of data acquisition.Keywords
This publication has 23 references indexed in Scilit:
- A Graph-based Recommendation across Heterogeneous Domains2015
- User Identification Across Social MediaACM Transactions on Knowledge Discovery From Data, 2015
- COSNET2015
- Detecting spammers on social networksNeurocomputing, 2015
- Identifying users in social networks with limited information2015
- Meta-path based multi-network collective link prediction2014
- Understanding Cross-site Linking in Online Social Networks2014
- Connecting users across social media sites2013
- Is more always merrier?2012
- A guided tour to approximate string matchingACM Computing Surveys, 2001