Análisis de Sentimiento en el dominio salud: analizando comentarios sobre fármacos

• Autores: Isabel Segura Bedmar , Paloma Martínez Fernández , Cristóbal Colón Ruiz
• Localización: Procesamiento del lenguaje natural, ISSN 1135-5948, Nº. 63, 2019, págs. 15-22
• Idioma: español
• Títulos paralelos:
  • Sentiment analysis on health domain: analyzing patient comments on drugs
• Enlaces
  • Texto completo
• Dialnet Métricas: 1 Cita
• Resumen
  • español

    En el análisis de sentimiento, la mayoría de las investigaciones han sido llevadas a cabo en dominios generales tales como en el análisis de opiniones de películas, restaurantes y otros productos o servicios, con escasa representación en el ámbito médico. Cada vez más, los pacientes buscan información en internet sobre los posibles beneficios, efectos adversos y opiniones que otros pacientes tiene sobre diferentes fármacos. El objetivo de este trabajo es predecir el grado de satisfacción de los pacientes respecto a un determinado fármaco en base a sus comentarios. Para llevar a cabo la tarea, hemos utilizado una colección de comentarios sobre diferentes tipos de fármacos y aplicado una red convolucional para la clasificación de los mismos. Los resultados muestran que este tipo de redes proporciona mejores resultados en términos de precisión, recall y f1-score que empleando algoritmos clásicos de clasificación como las máquinas de soporte vectorial.

  • English

    Most of the research in sentiment analysis has been conducted in general domains such as the analysis of film reviews, restaurants and other products or services, but without much representation in the medical field. Increasingly, patients are searching the internet for information about the potential benefits, adverse effects and opinions that other patients have about different drugs. The aim of this work is to predict the degree of patient satisfaction with a given drug based on their reviews. To carry out the task, we have used a collection of reviews on different types of drugs and applied a convolutional network for their classification. The results show that this type of network provides better results in terms of precision, recall and f1-score than using classical classification algorithms such as vector support machines.

• Referencias bibliográficas
  • Baccianella, S., A. Esuli, y F. Sebastiani. 2010. Sentiwordnet 3.0: an enhanced lexical resource for sentiment analysis and opinion mining....
  • Boureau, Y.-L., F. Bach, Y. LeCun, y J. Ponce. 2010. Learning mid-level features for recognition.
  • Collobert, R. y J. Weston. 2008. A unified architecture for natural language processing: Deep neural networks with multitask learning. En...
  • De Marneffe, M.-C., B. MacCartney, y C. D. Manning. 2006. Generating typed dependency parses from phrase structure parses. En Proceedings...
  • Denecke, K. y Y. Deng. 2015. Sentiment analysis in medical settings: New opportunities and challenges. Artificial Intelligence in Medicine,...
  • Er, M. J., Y. Zhang, N. Wang, y M. Pratama. 2016. Attention pooling-based convolutional neural network for sentence modelling. Information...
  • Frakes, W. B. y R. Baeza-Yates. 1992. Information retrieval: Data structures & algorithms, volumen 331. Prentice Hall Englewood Cliffs,...
  • Gopalakrishnan, V. y C. Ramaswamy. 2017. Patient opinion mining to analyze drugs satisfaction using supervised learning. Journal of applied...
  • Gräßer, F., S. Kallumadi, H. Malberg, y S. Zaunseder. 2018. Aspect-based sentiment analysis of drug reviews applying cross-domain and cross-data...
  • Ide, H. y T. Kurita. 2017. Improvement of learning for cnn with relu activation by sparse regularization. En 2017 International Joint Conference...
  • Joachims, T. 1998. Text categorization with support vector machines: Learning with many relevant features. En European conference on machine...
  • Kim, Y. 2014. Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882.
  • Kingma, D. P. y J. Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
  • Liu, B. 2012. Sentiment analysis and opinion mining. Synthesis lectures on human language technologies, 5(1):1–167.
  • Mikolov, T., I. Sutskever, K. Chen, G. Corrado, y J. Dean. 2013. Distributed representations of words and phrases and their compositionality.
  • Na, J. y W. Y. M. Kyaing. 2015. Sentiment analysis of user-generated content on drug review websites. Journal of Information Science Theory...
  • Na, J.-C., W. Y. M. Kyaing, C. S. Khoo, S. Foo, Y.-K. Chang, y Y.-L. Theng. 2012. Sentiment classification of drug reviews using a rule-based...
  • Nair, V. y G. E. Hinton. 2010. Rectified linear units improve restricted boltzmann machines. En Proceedings of the 27th international conference...
  • Pang, B. y L. Lee. 2008. Opinion mining and sentiment analysis. Foundations and Trends R in Information Retrieval, 2(1–2):1–135.
  • Pyysalo, S., F. Ginter, H. Moen, T. Salakoski, y S. Ananiadou. 2013. Distributional semantics resources for biomedical text processing.
  • Suárez-Paniagua, V. y I. Segura-Bedmar. 2018. Evaluation of pooling operations in convolutional architectures for drug-drug interaction extraction....
  • Wang, J., Z. Wang, D. Zhang, y J. Yan. 2017. Combining knowledge with deep convolutional neural networks for short text classification. En...
  • Wilson, T., J. Wiebe, y P. Hoffmann. 2005. Recognizing contextual polarity in phraselevel sentiment analysis. En Proceedings of Human Language...
  • Yadav, S., A. Ekbal, S. Saha, y P. Bhattacharyya. 2018. Medical sentiment analysis using social media: Towards building a patient assisted...