Compare Esuli and Sebastiani LREC 2006 vs. Esuli and Sebastiani EACL 2006

From Cohen Courses
Jump to navigationJump to search

Papers

  • Esuli and Sebastiani LREC 2006 Andrea Esuli and Fabrizio Sebastiani. SentiWordNet: A Publicly Available Lexical Resource for Opinion Mining. In Proceedings of the 5th Conference on Language Resources and Evaluation (LREC 2006), Genova, IT, 2006, pp. 417-422. pdf
  • Determining term subjectivity and term orientation for opinion mining. Andrea Esuli and Fabrizio Sebastiani. Determining term subjectivity and term orientation for opinion mining. In Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2006), Trento, IT, 2006, pp. 193-200. pdf

Comparison

The two papers describe essentially the same algorithm of classification of terms into three categories: Positive, Negative and Objective, thereby combining two separate problems: term subjectivity and term orientation for opinion mining applications. The semi-supervised learning is used to build a labeled set of examples from the three categories. WordNet glosses are used to build vectorial representation for each synset. Then, standard supervised learning algorithms are employed to label the WordNet terms.

There are two differences in these approaches: (1) while the EACL paper uses synonymy and direct antonymy between terms to propagate labels in semi-supervised stage, the LREC paper is navigating the relations of direct antonymy, similarity, derivedfrom, pertains-to, attribute, and also-see relations. (2) in the EACL paper the authors compare three different supervised classifiers, while in the LREC paper they use the ensemble of these classifiers.

Both papers have the same 'Big idea', use the same datasets and aim to solve the same problem. The main difference is the focus of the papers: while the EACL paper presents the novel approach to the opinion mining problem solution, the LREC paper provides useful resources obtained from this work: the SentiWordNet and the visualization tool.

Additional Questions

How much time did you spend reading the (new, non-wikified) paper you summarized? 2 hours

How much time did you spend reading the old wikified paper? 1 hour

How much time did you spend reading the summary of the old paper? 20 minutes

How much time did you spend reading background material? 20 minutes

Was there a study plan for the old paper? Yes

If so, did you read any of the items suggested by the study plan? and how much time did you spend with reading them? No.