Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
Using early view patterns to predict the popularity of youtube videos
These proposed models lead to significant decreases in relative squared errors, reaching up to 20% reduction on average, and larger reductions for videos that experience a high peak in popularity in their early days followed by a sharp decrease in popularity.
A brief survey of automatic methods for author name disambiguation
- Anderson A. Ferreira, Marcos André Gonçalves, Alberto H. F. Laender
- Computer ScienceSGMD
- 17 August 2012
A taxonomy for characterizing the current author name disambiguation methods described in the literature is proposed, a brief survey of the most representative ones is presented and several open challenges are discussed.
Streams, structures, spaces, scenarios, societies (5s): A formal model for digital libraries
The fundamental abstractions of Streams, Structures, Spaces, Scenarios, and Societies (5S), which allow us to define digital libraries rigorously and usefully, are proposed.
Detecting Spammers and Content Promoters in Online Video Social Networks
- Fabrício Benevenuto, Tiago Rodrigues, Virgílio A. F. Almeida, J. Almeida, Marcos André Gonçalves
- Computer ScienceIEEE INFOCOM Workshops
- 19 July 2009
This paper manually builds a test collection of real YouTube users, classifying them as spammers, promoters, and legitimates, and provides a characterization of social and content attributes that may help distinguish each user class.
SentiBench - a benchmark comparison of state-of-the-practice sentiment analysis methods
- Filipe Nunes Ribeiro, Matheus Araújo, P. Gonçalves, Marcos André Gonçalves, Fabrício Benevenuto
- Computer ScienceEPJ Data Science
- 6 December 2015
A benchmark comparison of twenty-four popular sentiment analysis methods, covering messages posted on social networks, movie and product reviews, as well as opinions and comments in news articles is presented, highlighting the extent to which the prediction performance of these methods varies considerably across datasets.
A source independent framework for research paper recommendation
- C. Nascimento, Alberto H. F. Laender, A. D. Silva, Marcos André Gonçalves
- Computer ScienceJCDL '11
- 13 June 2011
This paper proposes a novel source independent framework for research paper recommendation that requires as input only a single research paper and generates several potential queries by using terms in that paper, which are then submitted to existing Web information sources that hold research papers.
Exploiting user feedback to learn to rank answers in q&a forums: a case study with stack overflow
The authors' L2R method was trained to learn the answer rating, based on the feedback users give to answers in Q&A forums, and was able to outperform a state of the art baseline with gains of up to 21% in NDCG, a metric used to evaluate rankings.
Learning to advertise
- A. Lacerda, Marco Cristo, Marcos André Gonçalves, W. Fan, N. Ziviani, B. Ribeiro-Neto
- Computer ScienceSIGIR
- 6 August 2006
A new framework for associating ads with web pages based on Genetic Programming (GP), which aims at learning functions that select the most appropriate ads, given the contents of a Web page to optimize overall precision and minimize the number of misplacements.
Using web information for author name disambiguation
- D. Pereira, B. Ribeiro-Neto, N. Ziviani, Alberto H. F. Laender, Marcos André Gonçalves, Anderson A. Ferreira
- Computer ScienceJCDL '09
- 15 June 2009
Results show that the method yields results that outperform those of two state-of-the-art unsupervised methods and are statistically comparable with those of a supervised one, but requiring no training.
An unsupervised heuristic-based hierarchical method for name disambiguation in bibliographic citations
- Ricardo G. Cota, Anderson A. Ferreira, C. Nascimento, Marcos André Gonçalves, Alberto H. F. Laender
- Computer Science
- 1 September 2010
The results show that the unsupervised method, when using all attributes, performs competitively against all other methods, under both metrics, loosing only in one case against a supervised method, whose result was very close to the authors'.