Prototipo de un clasificador de sentimientos para chats de atención al cliente en canales digitales del sector salud

dc.contributor.advisorVelásquez Henao, Juan David
dc.contributor.authorArdila Franco, César Augusto
dc.date.accessioned2023-06-09T14:42:59Z
dc.date.available2023-06-09T14:42:59Z
dc.date.issued2023-01-19
dc.descriptionilustraciones, diagramasspa
dc.description.abstractEl presente trabajo evalúa el modelo Pysentimiento para extraer la polaridad (negativo, neutro o positivo) de mensajes que pertenecen a un canal digital del sector salud y propone un esquema compuesto por tres subsistemas para incrementar el rendimiento del clasificador de emociones: 1) aplicar el preprocesamiento correcto los mensajes del corpus; 2) generar una tabla de expresiones comunes que facilite la clasificación de mensajes con polaridad neutra (NEU) y 3) construir un sistema de alerta que permita a los analistas identificar cuándo la predicción de un sentimiento puede considerarse ambigua. El nuevo esquema, además de presentar un incremento en rendimiento, permite también gestionar la información con el objetivo de caracterizar los mensajes de canales digitales del sector salud, y por ende, facilitar la implementación de nuevos clasificadores de emociones. (Texto tomado de la fuente)spa
dc.description.abstractThis paper evaluates a model called Pysentimiento to extract the polarity (negative, neutral, or positive) of messages that belong to a digital channel in the health sector. It also proposes a scheme made up of three subsystems to increase the performance of the sentiment classifier: 1) apply the correct preprocessing to the corpus messages; 2) generate a table of common expressions that facilitates the classification of messages with neutral polarity (NEU) and 3) build an alert system that allows analysts to identify when the prediction of a sentiment can be considered ambiguous. The new scheme, in addition to presenting an increase in performance, also makes it possible to manage the information in order to characterize the messages from digital channels in the health sector, and therefore, facilitate the implementation of new emotion classifiers.eng
dc.description.curricularareaÁrea Curricular de Ingeniería de Sistemas e Informáticaspa
dc.description.degreelevelMaestríaspa
dc.description.degreenameMagíster en Ingeniería - Analíticaspa
dc.description.researchareaAnalítica Predictivaspa
dc.format.extent66 páginasspa
dc.format.mimetypeapplication/pdfspa
dc.identifier.instnameUniversidad Nacional de Colombiaspa
dc.identifier.reponameRepositorio Institucional Universidad Nacional de Colombiaspa
dc.identifier.repourlhttps://repositorio.unal.edu.co/spa
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/84001
dc.language.isospaspa
dc.publisherUniversidad Nacional de Colombiaspa
dc.publisher.branchUniversidad Nacional de Colombia - Sede Medellínspa
dc.publisher.facultyFacultad de Minasspa
dc.publisher.placeMedellín, Colombiaspa
dc.publisher.programMedellín - Minas - Maestría en Ingeniería - Analíticaspa
dc.relation.indexedRedColspa
dc.relation.indexedLaReferenciaspa
dc.relation.referencesF. Reichheld, «The one number you need to grow,» Harvard business review, vol. 81, nº 124, pp. 46-54, 2003.spa
dc.relation.referencesB. Lakdawala, F. Khan, A. Khan, Y. Tomar, R. Gupta y A. Shaikh, «Voice to Text transcription using CMU Sphinx A mobile application for healthcare organization,» de Second International Conference on Inventive Communication and Computational Technologies (ICICCT), 2018.spa
dc.relation.referencesS. Liu, «Bridging Text Visualization and Mining: A Task-Driven Survey,» IEEE Transactions on Visualization and Computer Graphics, vol. 25, nº 7, pp. 2482-2504, 2019.spa
dc.relation.referencesS. Loria, «textblob Documentation,» Release 0.15, vol. 2, 2018.spa
dc.relation.referencesJ. M. Pérez, J. C. Giudici y F. Luque, «pysentimiento: A Python Toolkit for Sentiment Analysis and SocialNLP tasks,» 2021.spa
dc.relation.referencesA. Krizhevsky, I. Sutskever y G. E. Hinton, «Imagenet classification with deep convolutional neural networks,» de Neural. Information Processing Systems (NIPS), 2012.spa
dc.relation.referencesK. V. Raju y M. Sridhar, «Sentimental Analysis Inclination, A Review,» de International Conference on Current Trends in Computer, Electrical, Electronics and Communication (CTCEEC), 2017.spa
dc.relation.referencesM. T. Pilehvar y J. Camacho-Collados, «Embeddings in Natural Language Processing: Theory and Advances in Vector Representations of Meaning, Morgan & Claypool,» 2020.spa
dc.relation.referencesA. Vaswani, «Attention is all you need,» Advances in Neural Information Processing Systems, pp. 5998-6008, 2017.spa
dc.relation.referencesJ. Canete, Chaperon, Gabriel, Fuentes, Rodrigo, J.-H. Ho, Kang, Hojin y J. Pérez, «Spanish pre-trained bert model and evaluation data,» Pml4dc at iclr, 2020.spa
dc.relation.referencesT. Young, D. Hazarika, S. Poria y E. Cambria, «Recent Trends in Deep Learning Based Natural Language Processing,» IEEE Computational Intelligence Magazine, vol. 13, nº 3, pp. 55-75, 2018.spa
dc.relation.referencesS. Yang, Z. Ning y Y. Wu, «NLP Based on Twitter Information: A Survey Report,» de 2nd International Conference on Information Technology and Computer Application (ITCA), 2020.spa
dc.relation.referencesS. Z. Mishu y S. M. Rafiuddin, «Performance analysis of supervised machine learning algorithms for text classification,» de 19th International Conference on Computer and Information Technology (ICCIT), 2016.spa
dc.relation.referencesAggarwal, C. Charu y C. Zhai, «A survey of text classification algorithms,» Springer US, pp. 163-222, 2012.spa
dc.relation.referencesLi, Xiaoli y B. Liu, «Learning to classify texts using positive and unlabeled data,» IJCAI, vol. 3, 2003.spa
dc.relation.referencesTong, Simon y D. Koller, «Support vector machine active learning with applications to text classification,» Journal of machine learning research 2, pp. 45-66, 2001.spa
dc.relation.referencesLiu y Bing, «Text classification by labeling words,» AAAI, vol. 4, 2004.spa
dc.relation.referencesSchütze y Hinrich, «Introduction to Information Retrieval,» de Proceedings of the international communication of association for computing machinery conference, 2008.spa
dc.relation.referencesTang y Bo, «A Bayesian classification approach using class-specific features for text categorization,» IEEE Transactions on Knowledge and Data Engineering, vol. 28, nº 6, pp. 1602-1606, 2016.spa
dc.relation.referencesS. J. S. a. G. M. N. Arunachalam, «A survey on text classification techniques for sentiment polarity detection,» Innovations in Power and Advanced Computing Technologies (i-PACT), pp. 1-5, 2017.spa
dc.relation.referencesZ. Li, W. Shang y M. Yan, «News text classification model based on topic model,» 2016.spa
dc.relation.referencesM. I. Khaleel, I. I. Hmeidi y H. M. Najadat, «An Automatic Text Classification System Based on Genetic Algorithm,» 2016.spa
dc.relation.referencesJ. Devlin, M. W. Chang, K. Lee y K. Toutanova, «Bert: Pre-training of deep bidirectional transformers for language understanding,» arXiv preprint.spa
dc.relation.referencesM. E. Peters, M. Neumann, M. Iyyer, M. Gardner, C. Clark, K. Lee y L. Zettlemoyer, «Deep contextualized word representations,» arXiv preprint, 2018.spa
dc.relation.referencesJ. Howard y S. Ruder, «Universal language model fine-tuning for text classification,» arXiv preprint, 2018.spa
dc.relation.referencesJ. Ara, M. T. Hasan, A. A. Omar y H. Bhuiyan, «Understanding Customer Sentiment: Lexical Analysis of Restaurant Reviews,» de IEEE Region 10 Symposium (TENSYMP), 2020.spa
dc.relation.referencesM. N. a. S. Yi, «The Impact of Sentiment Analysis on Social Media to Assess Customer Satisfaction: Case of Rwanda,» de IEEE 4th International Conference on Big Data Analytics (ICBDA), 2019.spa
dc.relation.referencesS. Lam, C. Chen, K. Kim, G. Wilson, J. H. Crew y M. S. Gerber, «Optimizing Customer-Agent Interactions with Natural Language Processing and Machine Learning,» de Systems and Information Engineering Design Symposium (SIEDS), 2019.spa
dc.relation.referencesC. A. Haryani, A. N. Hidayanto, N. F. A. Budi y Herkules, «Sentiment Analysis of Online Auction Service Quality on Twitter Data: A case of E-Bay,» de 6th International Conference on Cyber and IT Service Management (CITSM), 2018.spa
dc.relation.referencesD. Wu, «A big data analytics framework for forecasting rare customer complaints: A use case of predicting MA members complaints to CMS,» de IEEE International Conference on Big Data (Big Data), 2017.spa
dc.relation.referencesA. I. Pandesenda, R. R. Yana, E. A. Sukma, A. Yahya, P. Widharto y A. N. Hidayanto, «Sentiment Analysis of Service Quality of Online Healthcare Platform Using Fast Large-Margin,» de International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS), 2020.spa
dc.relation.referencesG. Saranya, G. Geetha, C. K, M. K y S. Karpagaselvi, «Sentiment analysis of healthcare Tweets using SVM Classifier,» de International Conference on Power, Energy, Control and Transmission Systems (ICPECTS), 2020.spa
dc.relation.referencesF. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion y O. o. Grisel, «Scikit-learn: Machine learning in Python,» Journal of Machine Learning Research, vol. 12, pp. 2825-2830, 2011.spa
dc.relation.referencesM. G. Vega, M. C. Díaz y others, Overview of TASS 2020: Introducing Emotion Detection, IberLEF@SEPLN, 2020.spa
dc.relation.referencesM. U. SALUR y İ. AYDIN, «The Impact of Preprocessing on Classification Performance in Convolutional Neural Networks for Turkish Text,» de International Conference on Artificial Intelligence and Data Processing (IDAP), 2018.spa
dc.relation.referencesP. Chandrasekar y K. Qian, «The Impact of Data Preprocessing on the Performance of a Naive Bayes Classifier,» de IEEE 40th Annual Computer Software and Applications Conference (COMPSAC), 2016.spa
dc.relation.referencesA. Kurbatow, «The research of text preprocessing effect on text documents classification efficiency,» de International Conference "Stability and Control Processes" in Memory of V.I. Zubov (SCP), 2015.spa
dc.relation.referencesA. K. B y M. M. Kodabagi, «Efficient Data Preprocessing approach for Imbalanced Data in Email Classification System,» de International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE), 2020.spa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.licenseAtribución-NoComercial-SinDerivadas 4.0 Internacionalspa
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/spa
dc.subject.lembRedes socialesspa
dc.subject.lembSocial networkseng
dc.subject.proposalAnalítica de textospa
dc.subject.proposalModelos de clasificación textualspa
dc.subject.proposalAnálisis de polaridadspa
dc.subject.proposalBussiness Processing Outsourcing (BPO)eng
dc.subject.proposalCanales digitalesspa
dc.subject.proposalSector saludspa
dc.subject.proposalText analyticseng
dc.subject.proposalText classification modelseng
dc.subject.proposalPolarity analysiseng
dc.subject.proposalDigital channelseng
dc.subject.proposalHealth sectoreng
dc.subject.proposalExternalización de Procesos de Negociospa
dc.titlePrototipo de un clasificador de sentimientos para chats de atención al cliente en canales digitales del sector saludspa
dc.title.translatedPrototype of a sentiment classifier for customer service chats in digital channels of the health sectoreng
dc.typeTrabajo de grado - Maestríaspa
dc.type.coarhttp://purl.org/coar/resource_type/c_bdccspa
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.type.contentTextspa
dc.type.driverinfo:eu-repo/semantics/masterThesisspa
dc.type.redcolhttp://purl.org/redcol/resource_type/TMspa
dc.type.versioninfo:eu-repo/semantics/acceptedVersionspa
dcterms.audience.professionaldevelopmentInvestigadoresspa
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2spa

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
1144098500.2023.pdf
Tamaño:
1.23 MB
Formato:
Adobe Portable Document Format
Descripción:
Tesis de Maestría en Ingeniería - Analítica

Bloque de licencias

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
license.txt
Tamaño:
5.74 KB
Formato:
Item-specific license agreed upon to submission
Descripción: