Distinguishing between positive and negative opinions with complex network features

Authors:
Diego R. Amancio;Renato Fabbri;Osvaldo N. Oliveira, Jr.;Maria G. V. Nunes;Luciano da F. Costa
Affiliations:
University of São Paulo, São Carlos, São Paulo, Brazil;University of São Paulo, São Carlos, São Paulo, Brazil;University of São Paulo, São Carlos, São Paulo, Brazil;University of São Paulo, São Carlos, São Paulo, Brazil;University of São Paulo, São Carlos, São Paulo, Brazil
Venue:
TextGraphs-5 Proceedings of the 2010 Workshop on Graph-based Methods for Natural Language Processing
Year:
2010

Citing 8
Cited 1

C4.5: programs for machine learning

C4.5: programs for machine learning
Foundations of statistical natural language processing

Foundations of statistical natural language processing
Networks analysis, complexity, and brain function

Complexity - Special issue: Selection, tinkering, and emergence in complex networks
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
A complex network approach to text summarization

Information Sciences: an International Journal
A survey on sentiment detection of reviews

Expert Systems with Applications: An International Journal
A study of cross-validation and bootstrap for accuracy estimation and model selection

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Estimating continuous distributions in Bayesian classifiers

UAI'95 Proceedings of the Eleventh conference on Uncertainty in artificial intelligence

Corpus-based approaches to processing the scope of negation cues: an evaluation of the state of the art

IWCS '11 Proceedings of the Ninth International Conference on Computational Semantics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Topological and dynamic features of complex networks have proven to be suitable for capturing text characteristics in recent years, with various applications in natural language processing. In this article we show that texts with positive and negative opinions can be distinguished from each other when represented as complex networks. The distinction was possible by obtaining several metrics of the networks, including the in-degree, out-degree, shortest paths, clustering coefficient, betweenness and global efficiency. For visualization, the obtained multidimensional dataset was projected into a 2-dimensional space with the canonical variable analysis. The distinction was quantified using machine learning algorithms, which allowed an recall of 70% in the automatic discrimination for the negative opinions, even without attempts to optimize the pattern recognition process.