UNA REVISIÓN A LA MINERIA DE OPINIONES Y LOS RETOS DEL PNL

A review of opinion mining and NLP challenges

En los últimos años se ha generado un crecimiento en el análisis de las redes sociales para tener una idea de lo que la gente piensa sobre los temas de interés actuales, sin embargo, los sistemas de minería de texto originalmente diseñados para tipos de textos más regulares, como los artículos de noticias, pueden necesitar adaptarse para tratar publicaciones de redes sociales como Facebook, tweets, etc. En este artículo, se presenta una reflexión sobre temas relacionados con la minería de opinión de las redes sociales y los desafíos que imponen en un sistema de procesamiento de lenguaje natural (PNL).

DOI: http://dx.doi.org/10.21017/rimci.2020.v7.n13.a80

1. E. Boiy, Pieter Hens, Koen Deschacht, and Marie-Francine Moens. Automatic sentiment analysis of onlinetext. InProc. of the 11th International Conference on Electronic Publishing, Vienna, Austria. 2007.
2. A. Aue and M. Gamon. Customizing sentiment classifiers to new domains: a case study. InProc. of the International Conference on Recent Advances in Natural Language Processing, Borovetz, Bulgaria. 2015.
3. J. Blitzer, M. Dredze, and F. Pereira. Biographies, bollywood, boomboxes and blenders: Domain adaptation for sentiment classification. In Annual Meeting-Association For Computational Linguistics, page 440. 2007.
4. Bo Pang and Lillian Lee. Opinion mining and sentiment analysis.Information Retrieval, 2(1). 2008.
5. A. Popescu and O. Etzioni. Extracting product features and opinions from reviews. InProc. of the Conference on Empirical Methods for Natural Language Pro-cessing (EMNLP), pages 339–346, Vancouver, Canada. 2005.
6. A. Scharl and A. Weichselbraun. An automated ap-proach to investigating the online media coverage of USpresidential elections.Journal of Information Technol-ogy and Politics, 5(1):121–132. 2008.
7. M. Taboada, J. Brooke, M. Tofiloski, K. Voll, and M. Stede. Lexicon based methods for sentiment analysis. Computational Linguistics, 1(September 2010):1–41. 2011.
8. A. Pak and P. Paroubek. Twitter as a corpus forsentiment analysis and opinion mining. Proceedings of LREC. 2010.
9. A. C. Mullaly, C.L. Gagné, T.L. Spalding, and K.A.Marchak. Examining ambiguous adjectives inadjective noun phrases: Evidence for representation as ashared core meaning. The Mental Lexicon, 5(1):87–114. 2010.
10. A. Weichselbraun, S. Gindl, and A. Scharl. Acontext-dependent supervised learning approach to sen-timent detection in large textual databases. Journal of Information and Data Management, 1(3):329–342. 2010.
11. S. Gindl, A. Weichselbraun, and A. Scharl. Crossdomain contextualisation of sentiment lexicons. InProceedings of 19th European Conference on Artificial Intelligence (ECAI-2010), pages 771–776. 2010.
12. Johan Bollen and Huina Mao. Twitter mood as astock market predictor. IEEE Computer, 44(10):91–94. 2011.
13. H. Cunningham, D. Maynard, and V. Tablan. JAPE:a Java Annotation Patterns Engine (Second
14. Edition). Re-search Memorandum CS–00–10, Department of Computer Science, University of Sheffield, November. 2000.