Recommending Groups to Users based Both on Their Textual and Image Posts

Elias Oliveira, Howard Roatti, Gustavo Ramos Lima, Patrick Marques Ciarelli

2016

Abstract

This article focuses on the recommendation of Facebook groups to users, based on the post profile of each user on Facebook. In order to accomplish this task, texts and images provided by users are used as source of information, and the experiments showed that the combination of these two types of information gives results better than or equal to the results obtained when using separately these data. The proposed approach in this paper is simple and promising to recommend Facebook groups.

References

  1. Baeza-Yates, R. and Ribeiro-Neto, B. (1998). Modern Information Retrieval. Addison-Wesley, New York, first edition edition.
  2. Barla, A., Odone, F., and Verri, A. (2003). Histogram intersection kernel for image classification.Proceedings of 2003 International Conference on Image Processing, 3:513-516.
  3. de Oliveira, M. G., Ciarelli, P. M., and Oliveira, E. (2013). Recommendation of programming activities by multi-label classification for a formative assessment of students. Expert Systems with Applications, 40(16):6641-6651.
  4. de Souza Gazolli, K. A. and Salles, E. O. T. (2012). A contextual image descriptor for scene classification. On-
Download


Paper Citation


in Harvard Style

Oliveira E., Roatti H., Ramos Lima G. and Marques Ciarelli P. (2016). Recommending Groups to Users based Both on Their Textual and Image Posts . In Proceedings of the 8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR, (IC3K 2016) ISBN 978-989-758-203-5, pages 315-320. DOI: 10.5220/0006053803150320


in Bibtex Style

@conference{kdir16,
author={Elias Oliveira and Howard Roatti and Gustavo Ramos Lima and Patrick Marques Ciarelli},
title={Recommending Groups to Users based Both on Their Textual and Image Posts},
booktitle={Proceedings of the 8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR, (IC3K 2016)},
year={2016},
pages={315-320},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006053803150320},
isbn={978-989-758-203-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR, (IC3K 2016)
TI - Recommending Groups to Users based Both on Their Textual and Image Posts
SN - 978-989-758-203-5
AU - Oliveira E.
AU - Roatti H.
AU - Ramos Lima G.
AU - Marques Ciarelli P.
PY - 2016
SP - 315
EP - 320
DO - 10.5220/0006053803150320