How opinion annotations and ontologies become objective?

Authors:
Aleksander Wawer;Krzysztof Sakwerda
Affiliations:
Institute of Computer Science, Polish Academy of Science, Warszawa, Poland;Institute of Computer Science, University of Wroclaw, Wroclaw, Poland
Venue:
SIIS'11 Proceedings of the 2011 international conference on Security and Intelligent Information Systems
Year:
2011

Citing 6
Cited 0

Comparison of Conceptual Graphs for Modelling Knowledge of Multiple Experts

ISMIS '96 Proceedings of the 9th International Symposium on Foundations of Intelligent Systems
Extracting product features and opinions from reviews

HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Fine-grained subjectivity and sentiment analysis: recognizing the intensity, polarity, and attitudes of private states

Fine-grained subjectivity and sentiment analysis: recognizing the intensity, polarity, and attitudes of private states
Mining opinion features in customer reviews

AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Feature subsumption for opinion analysis

EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
Conceptual graphs for a data base interface

IBM Journal of Research and Development

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe the methodology and the process of annotations of a corpus of reviews along with experiments on inter-annotator agreement. Our approach goes beyond "flat" sets of attributes and relies on more complex graph-alike ontologies to annotate the data. We propose and test an algorithm of automated induction of an ontology and compare the results with "manually" created ontologies and annotations. We conclude with a discussion of differences between the two approaches and annotator influence.