Mostrar el registro sencillo del ítem

dc.contributor.advisorCorzo Perez, Gerald Augusto
dc.contributor.advisorSantos Granados, German Ricardo
dc.contributor.advisorAngarita, Hector Andrés
dc.contributor.authorGonzález Ayala, Camilo Andrés
dc.date.accessioned2021-06-19T02:03:12Z
dc.date.accessioned2021-10-01T15:36:57Z
dc.date.available2021-06-19T02:03:12Z
dc.date.available2021-10-01T15:36:57Z
dc.date.issued2021
dc.identifier.urihttps://repositorio.escuelaing.edu.co/handle/001/1593
dc.description.abstractIn recent years, the community is much more participatory in the planning and decision-making processes of Integrated Water Resources Management. However, differences between competing stakeholders prevent the identification of important variables in decision-making. In addition, the COVID-19 situation has prevented activities from being face to face with the community where fundamental information is collected for the planning process. Faced with this panorama, and with the aim of complementing the characterization of a water system, and provide an alternative that collaborates in the planning and decision-making process, this research focuses on analyzing digital information sources from the public media, obtaining useful information from articles associated with a basin. The case study corresponds to La Paz - Choqueyapu river basin in Bolivia. The information from 6 representative newspapers of that country, related to water resources, was extracted. An exploratory analysis of the information is executed and it is associated with historical information on hydrological phenomena such as precipitation in the last decade, finding a good correlation between both sources of information. Through the application of Named Entity Recognition, it was possible to identify different entities associated with bodies of water, dams, authorities and communities that are present in the basin. Each of the articles is associated with a positive or negative sentiment according to its content in order to carry out a qualitative analysis of the basin. From the article and its associated sentiment, sentiment text classification models are build in the context of water resources with the extracted articles with different techniques of word embedding and classification machine learning algorithms. It was found that the model with the best performance corresponds to the SVM algorithm with linear kernel and Word2vec continuous bag of words word embedding, obtaining 84% accuracy. This result was compared with the value obtained through the Spanish Sentiment Analysis library of 63%, evidencing a high improvement in the classification of texts associated with water resources in the Spanish language. Finally, by finding the most frequent words in a positive or negative context, important variables can be evidenced for the improvement of the planning and decision-making process.eng
dc.description.abstractEn los últimos años, la comunidad es mucho más participativa en los procesos de planificación y toma de decisiones de la Gestión Integral de los Recursos Hídricos. Sin embargo, las diferencias entre actores que compiten entre sí impiden la identificación de variables importantes en la toma de decisiones. En Además, la situación de COVID-19 ha impedido que las actividades sean presenciales con la comunidad donde se recoge información fundamental para el proceso de planificación. Ante este panorama, y con el objetivo de complementar la caracterización de un sistema hídrico, y proporcionar una alternativa que colabore en el proceso de planificación y toma de decisiones, esta investigación se centra en el análisis de las fuentes de información digital de los medios de comunicación públicos, obteniendo información útil de los artículos asociados a una cuenca. El caso de estudio corresponde a La Paz - Cuenca del río Choqueyapu en Bolivia. La información de 6 periódicos representativos de ese país, relacionada con los recursos hídricos, fue extraída. Se realiza un análisis exploratorio de la información se ejecuta y se asocia con la información histórica de los fenómenos hidrológicos como precipitación en la última década, encontrando una buena correlación entre ambas fuentes de información. Mediante la aplicación del Reconocimiento de Entidades Nombradas, se logró identificar diferentes entidades asociadas a cuerpos de agua, presas, autoridades y comunidades que están presentes en la cuenca. A cada uno de los artículos se le asocia un sentimiento positivo o negativo según su contenido para realizar un análisis cualitativo de la cuenca. A partir del artículo y su de los artículos y su sentimiento asociado, se construyen modelos de clasificación de textos de sentimiento en el contexto de los recursos hídricos con los artículos extraídos con diferentes de los recursos hídricos con los artículos extraídos con diferentes técnicas de incrustación de palabras y algoritmos de aprendizaje automático de clasificación. Se encontró que el modelo con mejor rendimiento corresponde al algoritmo SVM con kernel lineal y Word2vec continuous bag of words word embedding, obteniendo un 84% de precisión. Este resultado se comparó con el con el valor obtenido por la librería de Análisis de Sentimientos en Español del 63%, evidenciando una alta mejora en la clasificación de textos asociados a los recursos hídricos en el idioma español. español. Finalmente, al encontrar las palabras más frecuentes en un contexto positivo o negativo se pueden evidenciar variables importantes para la mejora del proceso de planificación y proceso de planificación y toma de decisiones.spa
dc.format.extent76 páginasspa
dc.format.mimetypeapplication/pdfeng
dc.language.isoengeng
dc.publisherEscuela Colombiana de Ingeniería Julio Garavitospa
dc.titleAn Exploratory Analysis of Digital Information using Natural Language Processing for the Planning and Decision Making Process of Water Resources in Boliviaeng
dc.typeTrabajo de grado - Maestríaspa
dc.type.versioninfo:eu-repo/semantics/publishedVersionspa
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2spa
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85spa
dc.description.degreelevelMaestríaspa
dc.description.degreenameMagíster en Ingeniería Civilspa
dc.identifier.urlhttps://catalogo.escuelaing.edu.co/cgi-bin/koha/opac-detail.pl?biblionumber=22679
dc.publisher.programMaestría en Ingeniería Civilspa
dc.relation.indexedN/Aspa
dc.relation.referencesAgramont, A., Craps, M., Balderrama, M., & Huysmans, M. (2019). Transdisciplinary learning communities to involve vulnerable social groups in solving complex water-related problems in Bolivia. Water (Switzerland), 11(2) doi:10.3390/w11020385eng
dc.relation.referencesAli Fauzi, M. (2019). Word2Vec model for sentiment analysis of product reviews in indonesian language. International Journal of Electrical and Computer Engineering, 9(1), 525-530. doi:10.11591/ijece.v9i1.pp.525-530eng
dc.relation.referencesAl-Saqqa, S., & Awajan, A. (2019). The use of Word2vec model in sentiment analysis: A survey. Paper presented at the ACM International Conference Proceeding Series, 39-43. doi:10.1145/3388218.3388229eng
dc.relation.referencesCarrera, J. S., Key, K., Bailey, S., Hamm, J. A., Cuthbertson, C. A., Lewis, E. Y., . . . Calhoun, K. (2019). Community science as a pathway for resilience in response to a public health crisis in flint, michigan. Social Sciences, 8(3) doi:10.3390/socsci8030094eng
dc.relation.referencesEkenga, C. C., McElwain, C. -., & Sprague, N. (2018). Examining public perceptions about lead in school drinking water: A mixed-methods analysis of twitter response to an environmental health hazard. International Journal of Environmental Research and Public Health, 15(1) doi:10.3390/ijerph15010162eng
dc.relation.referencesGalvez, V. & Rojas, R. (2019) Collaboration and Integrated Water Resources Management: A Literature Review. World Water Policy; 5 (179– 191). doi:10.1002/wwp2.12013eng
dc.relation.referencesGavilan, S., Pastore, J., Uranga, J., Ferral, A., Lighezzolo, R., & Aceñolaza, P. (2019). Metodología operativa para la obtención de datos históricos de precipitación a partir de la misión satelital Tropical Rainfall Measuring Mission. Validación de resultados con datos de pluviómetros. Revista de la Facultad de Agronomía. 118, 115-125. doi:10.24215/16699513e011.eng
dc.relation.referencesIlyas, S. H. W., Soomro, Z. T., Anwar, A., Shahzad, H., & Yaqub, U. (2020). Analyzing brexit's impact using sentiment analysis and topic modeling on twitter discussion. Paper presented at the ACM International Conference Proceeding Series, 1-6. doi:10.1145/3396956.3396973eng
dc.relation.referencesJames, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning: With applications in R.eng
dc.relation.referencesJaphne, A., & Murugeswari, R. (2020). Opinion mining based complex polarity shift pattern handling for improved sentiment classification. Paper presented at the Proceedings of the 5th International Conference on Inventive Computation Technologies, ICICT 2020, 323-329. doi:10.1109/ICICT48043.2020.9112565eng
dc.relation.referencesKalaivani, K. S., Kuppuswami, S., & Kanimozhiselvi, C. S. (2019). Use of NLP based combined features for sentiment classification. International Journal of Engineering and Advanced Technology, 9(1), 621-626. doi:10.35940/ijeat.F8290.109119eng
dc.relation.referencesMikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. Paper presented at the 1st International Conference on Learning Representations, ICLR 2013 - Workshop Track Proceedings.eng
dc.relation.referencesMurakami, A., Nasukawa, T., Watanabe, K., & Hatayama, M. (2020). Understanding requirements and issues in disaster area using geotemporal visualization of twitter analysis. IBM Journal of Research and Development, 64(1-2) doi:10.1147/JRD.2019.2962491eng
dc.relation.referencesMurphy, J. T., Ozik, J., Collier, N. T., Altaweel, M., Lammers, R. B., Kliskey, A., Alessa, L., Cason, D., & Williams, P. (2014). Water relationships in the U.S. southwest: Characterizing water management networks using natural language processing. Water (Switzerland), 6(6), 1601-1641. doi:10.3390/w6061601eng
dc.relation.referencesNalini, C., Kharabe, S., & Sangeetha, S. (2019). Efficient notes generation through information extraction. International Journal of Engineering and Advanced Technology, 8(6 Special Issue 2), 160-162. doi:10.35940/ijeat.F1041.0886S219eng
dc.relation.referencesNoga, J., & Wolbring, G. (2013). Perceptions of water ownership, water management, and the responsibility of providing clean water. Water (Switzerland), 5(4), 1865-1889. doi:10.3390/w5041865eng
dc.relation.referencesParlar, T., & Sarac, E. (2019). IWD based feature selection algorithm for sentiment analysis. Elektronika Ir Elektrotechnika, 25(1), 54-58. doi:10.5755/j01.eie.25.1.22736eng
dc.relation.referencesPurkey, D. R., Arias, M. I. E., Mehta, V. K., Forni, L., Depsky, N. J., Yates, D. N., & Stevenson, W. N. (2018). A philosophical justification for a novel analysis-supported, stakeholder-driven participatory process for water resources planning and decision making. Water (Switzerland), 10(8) doi:10.3390/w10081009eng
dc.relation.referencesReyes-Menendez, A., Saura, J. R., & Alvarez-Alonso, C. (2018). Understanding #worldenvironmentday user opinions in twitter: A topic-based sentiment analysis approach. International Journal of Environmental Research and Public Health, 15(11) doi:10.3390/ijerph15112537eng
dc.relation.referencesSharma, S., & Bansal, M. (2020). Real-time sentiment analysis towards machine learning. International Journal of Scientific and Technology Research, 9(2), 987-989.eng
dc.relation.referencesSingh, S., Ahmad, M., Bhattacharya, A., & Azhagiri, M. (2019). Predicting stock market trends using hybrid SVM model and LSTM with sentiment determination using natural language processing. International Journal of Engineering and Advanced Technology, 9(1), 2870-2875. doi:10.35940/ijeat.A1106.109119eng
dc.relation.referencesSubirats, L., Conesa, J., & Armayones, M. (2020). Biomedical holistic ontology for people with rare diseases. International Journal of Environmental Research and Public Health, 17(17), 1-11. doi:10.3390/ijerph17176038eng
dc.relation.referencesVan Cauwenbergh, N., Ballester Ciuró, A., & Ahlers, R. (2018). Participatory processes and support tools for planning in complex dynamic environments: A case study on web-GIS based participatory water resources planning in Almeria, Spain. Ecology and Society, 23(2) doi:10.5751/ES-09987-230202eng
dc.relation.referencesWang, Z., Ke, L., Cui, X., Yin, Q., Liao, L., Gao, L., & Wang, Z. (2017). Monitoring environmental quality by sniffing social media. Sustainability (Switzerland), 9(2) doi:10.3390/su9020085eng
dc.relation.referencesXiong, J., Hswen, Y., & Naslund, J. A. (2020). Digital surveillance for monitoring environmental health threats: A case study capturing public opinion from twitter about the 2019 Chennai water crisis. International Journal of Environmental Research and Public Health, 17(14), 1-15. doi:10.3390/ijerph17145077eng
dc.relation.referencesXu, S., Li, Y., & Wang, Z. (2018). Bayesian naïve bayes classifiers to text classification. Journal of Information Science, 44(1), 48-59. doi:10.1177/0165551516677946eng
dc.relation.referencesZhang, D., Qiang, M., Jiang, H., Wen, Q., An, N., & Xia, B. (2018). Social sensing system for water conservation project: A case study of the south-to-north water transfer project in china. Water Policy, 20(4), 667-691. doi:10.2166/wp.2018.141eng
dc.relation.referencesZheng, F., Simpson, A. R., & Zecchin, A. C. (2014). An efficient hybrid approach for multiobjective optimization of water distribution systems. Water Resources Research, 50(5), 3650-3671. doi:10.1002/2013WR014143eng
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.subject.armarcDesarrollo de recursos hídricos - Recursos naturales - Bolivia
dc.subject.armarcProcesamiento de lenguaje natural
dc.subject.armarcInformación digital -
dc.subject.proposalProcesamiento de lenguaje naturalspa
dc.subject.proposalRecursos Hídricosspa
dc.subject.proposalAlgoritmosspa
dc.subject.proposalNatural language processingeng
dc.subject.proposalWater Resourceseng
dc.subject.proposalAlgorithmseng
dc.subject.proposalAprendizaje Automáticoeng
dc.subject.proposalMachine Learningeng
dc.type.coarhttp://purl.org/coar/resource_type/c_bdccspa
dc.type.contentTextspa
dc.type.driverinfo:eu-repo/semantics/masterThesisspa
dc.type.redcolhttps://purl.org/redcol/resource_type/TMspa


Ficheros en el ítem

Thumbnail
Thumbnail

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem