Análisis de Sentimientos Aplicado a Referencias Bibliográficas
##plugins.themes.bootstrap3.article.main##
Resumen
Actualmente índices como el hindex, calculan el impacto de un artículo científico considerando solamente el número y la frecuencia con que una cita bibliográfica es mencionada, sin  tomar en cuenta el propósito ni la polaridad con que fue referenciada; éste método de cómputo  puede llevar a conclusiones equivocadas a la hora de valorar la contribución científica de algunos investigadores o el impacto de las revistas en las que publican. En este trabajo se propone complementar las medidas cuantitativas de impacto con criterios subjetivos usando Análisis de Sentimientos para detectarlos  en el contexto de citas bibliográficas dentro del texto de los artículos. Se presenta una visión general de lo que involucra el Análisis de Sentimientos basado en los enfoques de reconocimiento de patrones y aprendizaje automático; se plantea una propuesta de diseño que combine estas técnicas, las aplique en  referencias bibliográficas y obtenga nuevos elementos para una visión más completa de la influencia de un artículo en la literatura científica.
Â
Currently indexes like hindex, calculate the impact of a scientific article considering only the number and the frequency of citation mentions, regardless of the purpose or polarity that authors intended; this method of calculation may be misleading when evaluating the scientific contribution of some researchers or the impact of the journals in which they publish. This paper aims to complement quantitative measures of impact analysis using subjective criteria detected with Sentiment Analysis in the context of citations in the text of the articles. We present an overview of what is involved in Sentiment Analysis using different approaches: pattern recognition and machine learning based technologies; we present a design proposal that combines these techniques applied in the context of bibliographic references to obtain a more complete view of the influence of an article in the scientific literature.
Descargas
Descargas
Detalles del artículo
Citas
A. Abu-Jbara and D. R. Radev, (2012, June). Reference scope identification in citing sentences. In Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 80-90). Association for Computational Linguistics.
E. Boldrini, J. Fernández, J.M. Gómez and P. Martínez Barco. (2011). EmotiBlog: towards a finer-grained sentiment analysis and its application to opinion mining. Actas de las IV Jornadas TIMM.
X. Carreras, I. Chao, L. Padró and M. Padró. FreeLing: An Open-Source Suite of Language Analyzers Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC'04), 2004.
A. Esuli and F. Sebastiani (2006). SentiWordNet: A Publicly Available Lexical Resource for Opinion Mining. Proceedings of LREC 2006 - 5th Conference on Language Resources and Evaluation, 22-28/5/2006, Genova (IT).
J. Fernández, E. Boldrini, J. M. Gómez, and P. Martínez-Barco, (2011). Evaluating EmotiBlog robustness for sentiment analysis tasks. In Natural Language Processing and Information Systems (pp. 290-294). Springer Berlin Heidelberg.
G. Herlach, (1978). Can retrieval of information from citation indexes be simplified? Multiple mention of a reference as a characteristic of the link between cited and citing article. Journal of the American Society for Information Science, 29(6), 308-310.
J. E. Hirsch, (15 November 2005). An index to quantify an individual's scientific research output. PNAS 102 (46): 16569-16572.
K. Hiroshi, N. Tetsuya and W. Hideo, (2004, August). Deeper sentiment analysis using machine translation technology. In Proceedings of the 20th international conference on Computational Linguistics (p. 494). Association for Computational Linguistics.
D. Lin (2003). Dependency-based evaluation of MINIPAR. In Treebanks (pp. 317-329). Springer Netherlands.
H. Liu, (2004). MontyLingua: An end-to-end natural language processor with common sense. Available at http://web.media.mit.edu/hugo/montylingua
X. Liu, J. Zhang and C. Guo, (2012, October). Full-text citation analysis: enhancing bibliometric and scientific publication ranking. In Proceedings of the 21st ACM international conference on Information and knowledge management (pp. 1975-1979). ACM.
M. D. Lytras, and P. Ordonez de Pablos, (2009). Social Web Evolution: Integrating Semantic Applications and Web 2.0 Technologies. Information Science Reference-Imprint of: IGI Publishing.
R. Prabowo, and M. Thelwall, (2009). Sentiment analysis: A combined approach. Journal of Informetrics, 3(2), 143-157.
F. Radicchi, (2012). In science "there is no bad publicity": Papers criticized in comments have high scientific impact. Scientific reports, 2.
F. Sebastiani (2002). Machine Learning in Automated Text Categorization. ACM Computing Surveys, 34(1), 1-47.
Stanford NLP. http://nlp.stanford.edu/software/index. Shtml. Verificado por última vez: 04 October, 2013.
C. Strapparava and A. Valitutti, (2004). WordNet Affect: an Affective Extension of WordNet. In LREC (Vol. 4, pp. 1083-1086).
P. D. Turney, and M. L. Littman, (2003). Measuring praise and criticism: Inference of semantic orientation from association. ACM Transactions on Information Systems (TOIS), 21(4), 315-346.
P. Vossen, (1998). EuroWordNet: a multilingual database with lexical semantic networks. Boston: Kluwer Academic.