Big Data and Business Intelligence - recommender system using social networks for cold-start issue

• Grant number: 14/04851-8
• Support Opportunities: Regular Research Grants
• Start date: March 01, 2017
• End date: August 31, 2019
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Solange Nice Alves de Souza
• Grantee: Solange Nice Alves de Souza
• Host Institution: Escola Politécnica (EP). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• City of the host institution: São Paulo

Abstract

In the last years have been observed a great increase in daily collected data from the internet, mobile devices and computer systems, which are practically used in all human activity. Great part of these data comes from social network, blogs, photos and videos, sensors, besides data maintained on servers that stored web browsing logs and any user relevant action on web sites. The Big Data term refers to these kinds of data and its management requirements, which is more complex due to the volume, variety and velocity that characterise these data. Using and take advantage of this enormous amount of data is extremely complex for human without the computer aid. Recommender Systems aims to help users to find artefacts (products, documents, information, services) that might interest them. Data users are employed to do recommendations. Cold-start is characterized by lack of user data and the recommendation is very difficult in this context. In spite of the researches found in literature, the cold-start problem is still a challenge. There is no a unique solution that could be employed in different domains or situations. In this scenario, data extracted from social networks allow to do assertive recommendations to the user. This project introduces the solution for cold-start using only data extracted from social networks. (AU)

Scientific publications

(4)

(The scientific publications listed on this page originate from the Web of Science or SciELO databases. Their authors have cited FAPESP grant or fellowship project numbers awarded to Principal Investigators or Fellowship Recipients, whether or not they are among the authors. This information is collected automatically and retrieved directly from those bibliometric databases.)

GONZALEZ CAMACHO, LESLY ALEJANDRA; ALVES-SOUZA, SOLANGE NICE. Social network data to alleviate cold-start in recommender system: A systematic review. INFORMATION PROCESSING & MANAGEMENT, v. 54, n. 4, p. 529-544, JUL 2018. (14/04851-8)

GONZALEZ CAMACHO, LESLY ALEJANDRA; KERSUL FARIA, JOAO HENRIQUE; ALVES-SOUZA, SOLANGE NICE; LEITE FILGUEIRAS, LUCIA VILELA; FRED, A; FILIPE, J. Social Tracks: Recommender System for Multiple Individuals using Social Influence. KDIR: PROCEEDINGS OF THE 11TH INTERNATIONAL JOINT CONFERENCE ON KNOWLEDGE DISCOVERY, KNOWLEDGE ENGINEERING AND KNOWLEDGE MANAGEMENT - VOL 1: KDIR, v. N/A, p. 9-pg., 2019-01-01. (14/04851-8)

CONTRATRES, FELIPE G.; ALVES-SOUZA, SOLANGE N.; LEITE FILGUEIRAS, LUCIA VILELA; DESOUZA, LUIZ S.. Sentiment Analysis of Social Network Data for Cold-Start Relief in Recommender Systems. TRENDS AND ADVANCES IN INFORMATION SYSTEMS AND TECHNOLOGIES, VOL 2, v. 746, p. 11-pg., 2018-01-01. (14/04851-8)

GONZALEZ-CAMACHO, LESLY ALEJANDRA; KERSUL FARIA, JOAO HENRIQUE; MACHADO, LUCAS TORREAO; ALVES-SOUZA, SOLANGE NICE; ROCHA, A; ADELI, H; DZEMYDA, G; MOREIRA, F. Recommender System Based on the Friendship Between Social Network Users in a Cold-Start Scenario. INFORMATION SYSTEMS AND TECHNOLOGIES, WORLDCIST 2022, VOL 3, v. 470, p. 19-pg., 2022-01-01. (14/04851-8)