Réseau de neurones profond et SVM pour la classification de sentiments
作者： Abdelhalim Rafrafi , Vincent Guigue , Patrick Gallinari
DOI:
关键词:
摘要: Le developpement des forums, blogs et de la vente en ligne pousse les utilisateurs a laisser plus d’informations libre acces sur le web. Une partie ces informations decrit sentiments: elles permettent developper modeles d’analyse d’opinions faire sondages dans divers domaines recuperant simplement donnees textuelles. Nous proposons d’utiliser reseaux neurones pour apprendre classification efficaces. L’architecture retenue mele couches classiques convolution, elle permet projeter mots un espace semantique continu. avons compare notre travail avec modele SVM corpus multi-thematiques Amazon. Nos experiences aboutissent performances identiques aux l’etat l’art. Cependant se comportent differemment erreurs ne concernent pas memes documents: il est possible d’ameliorer combinant modeles.
archives-ouvertes.fr
asso-aria.org 参考文章(27)
Andrea Esuli, Fabrizio Sebastiani, SENTIWORDNET: A Publicly Available Lexical Resource for Opinion Mining language resources and evaluation. pp. 417- 422 ,(2006)
Arjun Mukherjee, Bing Liu, Improving Gender Classification of Blog Authors empirical methods in natural language processing. pp. 207- 217 ,(2010)
Fangtao Li, Xiaoyan Zhu, Minlie Huang, Sentiment analysis with global topics and local dependency national conference on artificial intelligence. pp. 1371- 1376 ,(2010)
David M Blei, Andrew Y Ng, Michael I Jordan, None, Latent dirichlet allocation Journal of Machine Learning Research. ,vol. 3, pp. 993- 1022 ,(2003) , 10.5555/944919.944937
V. P. Plagianakos, G. D. Magoulas, M. N. Vrahatis, Learning Rate Adaptation in Stochastic Gradient Descent Nonconvex Optimization and Its Applications. pp. 433- 444 ,(2001) , 10.1007/978-1-4613-0279-7_27
Xiaowen Ding, Bing Liu, Philip S. Yu, A holistic lexicon-based approach to opinion mining web search and data mining. pp. 231- 240 ,(2008) , 10.1145/1341531.1341561
Theresa Wilson, Janyce Wiebe, Paul Hoffmann, Recognizing contextual polarity in phrase-level sentiment analysis Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing - HLT '05. pp. 347- 354 ,(2005) , 10.3115/1220575.1220619
Xiaowen Ding, Bing Liu, The utility of linguistic rules in opinion mining international acm sigir conference on research and development in information retrieval. pp. 811- 812 ,(2007) , 10.1145/1277741.1277921
Alistair Kennedy, Diana Inkpen, SENTIMENT CLASSIFICATION of MOVIE REVIEWS USING CONTEXTUAL VALENCE SHIFTERS computational intelligence. ,vol. 22, pp. 110- 125 ,(2006) , 10.1111/J.1467-8640.2006.00277.X
Jun Zhao, Kang Liu, Gen Wang, Adding redundant features for CRFs-based sentence sentiment classification Proceedings of the Conference on Empirical Methods in Natural Language Processing - EMNLP '08. pp. 117- 126 ,(2008) , 10.3115/1613715.1613733