Aplicación de técnicas de Machine Learning para hacer análisis de polaridad de sentimientos en texto para detectar tendencias de opinión en plataformas online

Vista sencilla de ítem
dc.contributor.advisorAmaya, Sindy Paola
dc.contributor.authorGranados Figueroa, Juan David
dc.contributor.corporatenameUniversidad Santo Tomásspa
dc.contributor.cvlachttps://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000796425
dc.contributor.googlescholarhttps://scholar.google.es/citations?user=Gg2sofAAAAAJ&hl=es
dc.contributor.orcidhttps://orcid.org/0000-0002-1714-1593
dc.date.accessioned2021-07-15T20:12:06Z
dc.date.available2021-07-15T20:12:06Z
dc.date.issued2021-03-01
dc.descriptionInternet ha permitido a millones de personas conectarse y generar interacciones, como en las redes sociales, lo que ha generado mucha información no estructurada, que es difícil de analizar por un grupo de seres humanos, debido a su gran cantidad. En este trabajo se aplican técnicas de Machine Learning para analizar la polaridad de sentimiento en lenguaje español, de los comentarios de usuarios de Twitter acerca de diversos temas. El análisis de polaridad de sentimiento permite analizar las tendencias de opinión de una forma rápida y automática, permitiendo a las empresas y organización tener información valiosa para la toma de decisiones. Se implementan Redes Neuronales Recurrentes, las cuales son uno de los métodos que mejores resultados muestran para el análisis de secuencias, mediante la aplicación de Deep Learning, el cual pertenece al campo del Machine Learning y que, además, evita la necesidad de realizar extracción de características, lo cual conllevaría una minuciosa selección por parte de expertos de lenguaje. Se utiliza Keras para programar el modelo con tensorflow, y se obtienen resultados de exactitud muy cercanos a los sistemas más avanzados en el estado del arte. El modelo es entrenado con un Dataset de 49.444 oraciones etiquetadas con positivo o negativo, en base al corpus de TASS.spa
dc.description.abstractThe Internet has allowed millions of people to connect and generate interactions, as in social networks, which has generated a lot of unstructured information, which is difficult for a group of human beings to analyze, due to its large amount. In this work, Machine Learning techniques are applied to analyze the polarity of sentiment in Spanish language, of the comments of Twitter users about various topics. Sentiment polarity analysis allows you to analyze opinion trends quickly and automatically, allowing companies and organizations to have valuable information for decision-making. Recurrent Neural Networks are implemented, which are one of the methods that show the best results for sequence analysis, through the application of Deep Learning, which belongs to the field of Machine Learning and which, in addition, avoids the need to perform extraction of characteristics, which would require careful selection by language experts. Keras is used to program the model with tensorflow, and accuracy results are obtained very close to the most advanced systems in the state of the art. The model is trained with a Dataset of 49,444 sentences labeled with positive or negative, based on the TASS corpusspa
dc.description.degreelevelPregradospa
dc.description.degreenameIngeniero Electronicospa
dc.description.domainhttp://unidadinvestigacion.usta.edu.cospa
dc.format.mimetypeapplication/pdf
dc.identifier.citationGranados, Figueroa, J. D. (2021). Aplicación de técnicas de Machine Learning para hacer análisis de polaridad de sentimientos en texto para detectar tendencias de opinión en plataformas online. [Trabajo de pregrado, Universidad Santo Tomás]. Repositorio Institucional.spa
dc.identifier.instnameinstname:Universidad Santo Tomásspa
dc.identifier.reponamereponame:Repositorio Institucional Universidad Santo Tomásspa
dc.identifier.repourlrepourl:https://repository.usta.edu.cospa
dc.identifier.urihttp://hdl.handle.net/11634/34933
dc.language.isospa
dc.publisherUniversidad Santo Tomásspa
dc.publisher.branchCRAI-USTA Bogotáspa
dc.publisher.facultyFacultad de Ingeniería Electrónicaspa
dc.publisher.programPregrado Ingeniería Electrónicaspa
dc.relation.references[1] V. Kharde y P. S. Sonawane, «Sentiment Analysis of Twitter Data: A Survey of Techniques,» International Journal of Computer Aplications, vol. 139(11), pp. 5-15, 2016.spa
dc.relation.references[2] M. Atique y . H. P. Patil , «Sentiment Analysis for Social Media: A Survey,» de 2nd International Conference on Information Science and Security (ICISS), Seoul, 2015.spa
dc.relation.references[3] Y. LeCun, Y. Bengio y G. Hinton, «Deep Learning,» NATURE, vol. 521, pp. 436-444, 2015.spa
dc.relation.references[4] I. Goodfellow, Y. Bengio y A. Courville, Deep Learning, MIT Press, 2016.spa
dc.relation.references[5] J. Chung, C. Gulcehre, K. Cho y Y. Bengio, «Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling,» de NIPS Deep Learning and Representation Learning Workshop, 2014.spa
dc.relation.references[6] E. Martínez-Cámara y J. Villena-Román, «TASS - Workshop on Sentiment Analysis at SEPLN,» Procesamiento del Lenguaje Natural, vol. 50, pp. 37-44, 2013.spa
dc.relation.references[7] L. Rosenberg y N. Pescetelli , «Artificial Swarm Intelligence Amplifies Accuracy when Predicting Financial Markets,» de IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON), New York City, 2017.spa
dc.relation.references[8] S. Al-Saqqa, H. Abdel-Nabi y A. Awajan, «A Survey of Textual Emotion Detection,» de 2018 8th International Conference on Computer Science and Information Technology (CSIT), Amman, Jordan, 2018.spa
dc.relation.references[9] H. S. Kisan, H. A. Kisan y A. P. Suresh , «Collective intelligence & sentimental analysis of twitter data by using StandfordNLP libraries with software as a service (SaaS),» de IEEE international Conference on Computational Intelligence and Computing Research (ICCIC), Chennai, 2016.spa
dc.relation.references[10] K. Zvarevashe y O. O. Olugbara , «A framework for sentiment analysis with opinion mining of hotel reviews,» de 2018 Conference on Information Communications Technology and Society (ICTAS), Durban, South Africa, 2018.spa
dc.relation.references[11] A. Salinca, «Business Reviews Classification Using Sentiment Analysis,» de 17th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC), Timisoara, Romania, 2015.spa
dc.relation.references[12] the sckit-learn comunity, «sckit-learn,» 2010. [En línea]. Available: https://scikit-learn.org/stable/index.html. [Último acceso: 10 May 2019].spa
dc.relation.references[13] H. Kaur, V. Mangat y Nidhi , «A survey of sentiment analysis techniques,» de International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC), Palladam, India, 2017.spa
dc.relation.references[14] A. Patel y K. T. Arvind , «Sentiment Analysis by using Recurrent Neural Network,» de 2° Internacional conference on advanced computing software engineering (ICACSE-2019), 2019.spa
dc.relation.references[15] «IMBD Datasets,» [En línea]. Available: https://www.imdb.com/interfaces/. [Último acceso: 10 May 2020].spa
dc.relation.references[16] M. A. Paredes-Valverde, R. Colomo-Palacios, M. d. P. Salas-Zárate y R. Valencia-García, «Sentiment Analysis in Spanish for Improvement of Products and Services: A Deep Learning Approach,» Hindawi, Scientific Programming, vol. Volume 2017, 26 Oct 2017.spa
dc.relation.references[17] A. Radford, R. Jozefowicz y I. Sutskever, «Learning to Generate Reviews and Discovering Sentiment,» arVix preprint arXiv:1704.01444v2 [cs.LG], 6 Apr 2017.spa
dc.relation.references[18] J. ̃. Paulo Aires, C. Padilha, C. Quevedo y F. Meneguzzi, «A Deep Learning Approach to Classify Aspect-Level Sentiment using Small Datasets,» de International Joint Conference on Neuronal Networks (IJCNN), Rio de Janeiro, Brazil, 2018.spa
dc.relation.references[19] S. Chen, C. Peng y L. Cai, «A Deep Neural Network Model for Target-based Sentiment Analysis,» de International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil, 2018.spa
dc.relation.references[20] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, G. Aidan N. , L. Kaiser y I. Polosukhin, «Attention Is All You Need,» arXiv preprint arXiv:1706.03762v5 [cs.CL], 6 Dec 2017.spa
dc.relation.references[21] «BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,» arVix preprint arXiv:1810.04805v2 [cs.CL], 24 May 2019.spa
dc.relation.references[22] Z. Yang, Z. Dai, Y. Yang, J. Carbonell, R. Salakhutdinov y Q. V. Le, «XLNet: Generalized Autoregressive Pretraining for Language Understanding,» arVix preprinted arXiv:1906.08237v2 [cs.CL], 2 Jan 2020.spa
dc.relation.references[23] T. B. Brown∗, B. Mann, N. Ryder∗ y M. Subbiah∗, «Language Models are Few-Shot Learners,» arVix preprint arXiv:2005.14165v4 [cs.CL], 22 Jul 2020.spa
dc.relation.references[24] L. You y B. Tuncer, «Exploring public sentiments for livable places based on a crowdcalibrated sentimet analysis mechanism,» de IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), San Francisco, CA, 2016.spa
dc.relation.references[25] Q. Song, S. Almahdi y S. Y. Yang, «Entropy based measure sentiment analysis in the financial market,» de IEEE Symposium Series on Computational Intelligence (SSCI), Honolulu, Hl, 2017.spa
dc.relation.references[26] C. W. Park y D. R. Seo, «Sentiment analysis of Twitter corpus related to artificial intelligence assistants,» de 5th International Conference on Industrial Engineering and Applications (ICIEA), Singapore, 2018.spa
dc.relation.references[27] X. Yu, Y. Liu , X. Huang y A. An, «Mining Online Reviews for Predicting Sales Performance: A Case Study in the Movie Domain,» vol. 24, nº 4, pp. 720 - 734, 2010.spa
dc.relation.references[28] N. Buduma, Fundamentals of Deep Learning, First Edition ed., Sebastopol., CA 95472.: O'Reilly Media, Inc., 2017, pp. 1-37.spa
dc.relation.references[29] Y. Bengio, A. Courville y P. Vincent, «Representation Learning: A Review and New Perspectives,» IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, nº 8, pp. 1798-1828, Agosto 2013.spa
dc.relation.references[30] J. Schmidhuber, «Deep learning in neural networks: An overview,» Neural networks, vol. 61, pp. 85-117, 2015.spa
dc.relation.references[31] A. Graves, Supervised Sequence Labelling with Recurrent Neural Networks, vol. 385, New York: Springe, 2012.spa
dc.relation.references[32] F. Provost, T. Fawcett y R. Kohavi, «The Case against Accuracy Estimation for Comparing Induction Algorithms,» de Fiftteen Internacional Conference on Machine Learning (IMLC), Madison, Wi, 1998.spa
dc.relation.references[33] N. Chinchor, Ph.D, «MUC-4 EVALUATION METRICS,» de Fourth Message Uunderstanding Conference (MUC-4): Proceedings of a Conference Held in McLean, Virginia, June 16-18, 1992.spa
dc.relation.references[34] «scikit-learn, k-fold cross validation,» [En línea]. Available: http://scikit-learn.sourceforge.net/stable/modules/generated/sklearn.cross_validation.KFold.html. [Último acceso: 15 Jul 2020].spa
dc.relation.references[35] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever y R. Salakhutdinov, «Dropout: A Simple Way to Prevent Neural Networks from,» Journal of Machine Learning Research, vol. 15, pp. 1929-1958, 2014.spa
dc.relation.references[36] Google, «tensorflow,» [En línea]. Available: https://www.tensorflow.org/guide/. [Último acceso: 17 Abril 2020].spa
dc.relation.references[37] F. Chollet, «keras,» [En línea]. Available: https://keras.io/. [Último acceso: 17 04 2020].spa
dc.relation.references[38] «https://www.python.org/,» [En línea]. [Último acceso: 15 Feb 2020].spa
dc.relation.references[39] Google, «tensorflow keras,» [En línea]. Available: https://www.tensorflow.org/guide/keras/overview. [Último acceso: 10 Abril 2020].spa
dc.relation.references[40] Google, «Google Colaboratory,» 25 May 2020. [En línea]. Available: https://colab.research.google.com/notebooks/intro.ipynb.spa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccess
dc.rights.coarhttp://purl.org/coar/access_right/c_abf2
dc.rights.localAbierto (Texto Completo)spa
dc.subject.keywordMachine Learningspa
dc.subject.keywordSentiment Polarity Analysisspa
dc.subject.keywordRecurrent Neural Networkspa
dc.subject.lembInteligencia Artificialspa
dc.subject.lembProcesamiento Natural de Lenguajespa
dc.subject.lembAprendizaje Profundospa
dc.subject.proposalProcesamiento Natural de Lenguajespa
dc.subject.proposalRedes Neuronales Recurrentesspa
dc.subject.proposalInteligencia Artificialspa
dc.subject.proposalAprendizaje de Maquinaspa
dc.subject.proposalAprendizaje Profundospa
dc.subject.proposalAnálisis de Polaridad de Sentimientospa
dc.titleAplicación de técnicas de Machine Learning para hacer análisis de polaridad de sentimientos en texto para detectar tendencias de opinión en plataformas onlinespa
dc.typebachelor thesis
dc.type.categoryFormación de Recurso Humano para la Ctel: Trabajo de grado de Pregradospa
dc.type.coarhttp://purl.org/coar/resource_type/c_7a1f
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.driveinfo:eu-repo/semantics/bachelorThesis
dc.type.localTesis de pregradospa
dc.type.versioninfo:eu-repo/semantics/acceptedVersion

Archivos

Bloque original

Mostrando 1 - 3 de 3
Miniatura
Nombre:
2021juangranados.pdf
Tamaño:
1.08 MB
Formato:
Adobe Portable Document Format
Descripción:
Documento
Descargar
Miniatura
Nombre:
Carta_autorizacion_autoarchivo.pdf
Tamaño:
466.54 KB
Formato:
Adobe Portable Document Format
Descripción:
Carta Autorización
Descargar
Miniatura
Nombre:
Carta_aprobacion_Biblioteca. Granados Figueroa.pdf
Tamaño:
169.45 KB
Formato:
Adobe Portable Document Format
Descripción:
Carta Aprobación Facultad
Descargar

Bloque de licencias

Mostrando 1 - 1 de 1
Miniatura
Nombre:
license.txt
Tamaño:
807 B
Formato:
Item-specific license agreed upon to submission
Descripción:
Descargar

Colecciones

Pregrado Ingeniería Electrónica