Mining User Behavior in Location-Based Social Networks

• Grant number: 13/12191-5
• Support type: Scholarships in Brazil - Doctorate
• Effective date (Start): March 01, 2014
• Effective date (End): July 31, 2017
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal researcher: Alneu de Andrade Lopes
• Grantee: Jorge Carlos Valverde Rebaza
• Home Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

Location-based social networks (LBSN) are web platforms that reflect structures of social networks in the real world. In recent years, the study of LBSNs has attracted the attention of the scientific community, specially, because LBSNs consider information from user interactions and geographic location information for a period time, to develop applications such as location recommender systems, local travel planning systems and others. A specific problem in social network analysis is the exploration of the user dynamic behavior. In the context of LBSNs, the different proposals that explore user behaviors address only one problem, i.e., identification of dynamic patterns in user behavior, leaving open the exploration of two others problems: prediction of future structural changes and detection of unusual transitions in behaviors. Motivated by this gap, this project aims to investigate innovative techniques to effectively explore the various issues surrounding the user behaviors, considering the location history in a dynamic time domain. The scope of this proposal covers all stages of modeling a LBSN as well as the creation of a model of behavior based on the location information of users. The dynamic behavioral model to be developed in this project will build on the basis of existing behavioral models for traditional social networks. The results of this project will be validated in datasets available in the community of social networks analysis and data mining.

Scientific publications

(4)

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

CHERMAN, EVERTON ALVARES; SPOLAOR, NEWTON; VALVERDE-REBAZA, JORGE; MONARD, MARIA CAROLINA. Lazy Multi-label Learning Algorithms Based on Mutuality Strategies. JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, v. 80, n. 1, SI, p. S261-S276, DEC 2015. (11/22749-8, 10/15992-0, 11/02393-4, 13/12191-5)

BERTON, LILIAN; FALEIROS, THIAGO DE PAULO; VALEJO, ALAN; VALVERDE-REBAZA, JORGE; LOPES, ALNEU DE ANDRADE. RGCLI: Robust Graph that Considers Labeled Instances for Semi Supervised Learning. Neurocomputing, v. 226, p. 238-248, FEB 22 2017. (11/23689-9, 11/21880-3, 15/14228-9, 13/12191-5)

DRURY, BRETT; VALVERDE-REBAZA, JORGE; MOURA, MARIA-FERNANDA; LOPES, ALNEU DE ANDRADE. A survey of the applications of Bayesian networks in agriculture. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, v. 65, p. 29-42, OCT 2017. (15/14228-9, 11/20451-1, 13/12191-5)

VALVERDE-REBAZA, JORGE C.; ROCHE, MATHIEU; PONCELET, PASCAL; LOPES, ALNEU DE ANDRADE. The role of location and social strength for friendship prediction in location-based social networks. INFORMATION PROCESSING & MANAGEMENT, v. 54, n. 4, p. 475-489, JUL 2018. (15/14228-9, 13/12191-5)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

REBAZA, Jorge Carlos Valverde. Mining user behavior in location-based social networks. 2017. Doctoral Thesis - Universidade de São Paulo (USP). Instituto de Ciências Matemáticas e de Computação (ICMC/SB) São Carlos.