Novo artigo: BEATnIk: an algorithm to Automatic generation of educational description of movies

Logo CBIE 2017

O artigo recebeu Menção Honrosa no Brazilian Symposium on Computers in Education (Simpósio Brasileiro de Informática na Educação – SBIE 2017)


Vinicius Woloszyn, Guilherme Medeiros Machado, José Palazzo Moreira de Oliveira, Leandro Wives, Horacio Saggion

Resumo

Teachers and professors have increasingly employed different methods to enrich the learning of a subject in class, drive other assignments, and meet curriculum standards, are some examples of it. One of such methods is the use of movies as an alternative educational experience to support class discussions. In this sense, websites such as www.TeachWithMovies.com, arise as a valuable support to the creation of lesson plans. In this website, each movie is described as a lesson plan targeting the learn of a subject, the plans comprise the movie benefits and possible problems, a helpful background, the discussion and some interesting questions to be presented to the students. However, the creation of such lesson plan or even a simple educational description of the movie can demand much work and time, since the developed text must consider educational aspects of the movie. In this paper, we describe BEATnIk (Biased Educational Automatic Text Summarization) an algorithm to automatic generation of movie’s summaries, such algorithm favors educational aspects from the text to generate a biased educational summary. The algorithm input, are users’ comments about the each movie that has a lesson plan in the TeachWithMovies (TWM) website, and the user’s comments extracted from amazon’s website. BEATnIk constructs a complete graph for each movie where each sentence from the comments’ set becomes a node, and each edge weight is defined by the value of an adapted cosine similarity between the sentences. The algorithm then employs the PageRank to compute the centrality of each node. The intuition behind this approach is that central sentences highlight aspects of a movie that many other reviews frequently mention. In addition, BEATnIk takes into account keywords extracted from the lesson plans of TWM. The final educational summary is based on the centrality score of the sentences pondered by the presence of educational keywords. The comparison of our approach to TextRank, which is a Graph-based Automatic Text Summarization, revealed that BEATnIk generate summaries closer to the description of the movies in TWM. The experiments showed that our approach statistically outperforms the baseline in precision, and achieves better results both in recall and f-score using ROUGE-n, which is a set of metrics used for evaluating automatic summarization.


Texto completo: PDF

 

Announcement of 2016 Peter P. Chen Award: Prof. Oscar Pastor

On behalf of the ER Steering Committee, we are pleased to announce the winner of the 2016 Peter P. Chen Award: Oscar Pastor of the Universitat Politecnica de Valencia.

 Initiated by Elsevier in 2008 to celebrate the 25th anniversary of the journal Data and Knowledge Engineering, the Peter P. Chen Award honors one person each year for his or her outstanding contributions to the field of conceptual modeling.  The winner will receive a prize of $2500 sponsored by Elsevier Publishing Company, and also will give a keynote speech at the ER2016 conference to be held November 14-17 in Gifu, Japan.   

The selection process was done according to the following five criteria:

* Research: how well the nominee has helped advance the field of   conceptual modeling with his/her intellectual contributions.
* Service: participation in the organization of conceptual-modeling-related meetings and conferences and participation in editorial   boards of conceptual-modeling-related journals.
* Education: how effectively the nominee has mentored doctoral students  in conceptual modeling, produced researchers from their labs, and   also helped mentor young people in the field.
* Contribution to practice: the extent to which the nominee has   contributed to technology transfer, commercialization, and   industrial projects.
* International reputation: the extent to which the nominee’s work is   visible to and has diffused into the international community.
 
The 2016 selection committee consisted of Stephen Liddle, Heinrich Mayr, Carlo Batini, Tok Wang Ling, and Il-Yeol Song.  The committee reviewed the qualifications of the nominees, and chose Professor Pastor because he “has been a towering figure in the field of conceptual modeling for more than two decades”.  Prof. Pastor has contributed both through research and service to the community, and his work has had an impact both on research and practice.  On all of the criteria dimensions (research, service, education, practice, reputation), Oscar Pastor is exemplary.  He was previously recognized as an ER Fellow in 2010.  We extend our congratulations and best wishes to Dr. Pastor and his family.
 
Winners of the Peter P. Chen Award include:
  • 2016 Oscar Pastor, Universitat Politecnica de Valencia, Spain
  • 2015 Il-Yeol Song, Drexel University, USA
  • 2014 Antonio L. Furtado, Pontificia Univ. Catolica do Rio de Janeiro, Brazil
  • 2013 Carlo Batini, Universita degli Studi di Milano-Bicocca, Italy
  • 2012 Stefano Spaccapietra, Ecole Polytechnique Federale de Lausanne, Switzerland
  • 2011 Tok Wang Ling, National University of Singapore, Singapore
  • 2010 John Mylopoulos, University of Trento, Italy
  • 2009 David Embley, Brigham Young University, USA
  • 2008 Bernhard Thalheim, University of Kiel, Germany
More information about this award can be found at http://conceptualmodeling.org/PeterP.Chen_Awardees.html