Mostrar el registro sencillo del ítem
Desarrollo de un asesor normativo mediante inteligencia artificial para el reglamento estudiantil del Politécnico Grancolombiano
| dc.contributor.advisor | Ávila Buitrago, Gabriel Eduardo | |
| dc.contributor.author | Angel Castro, Jeison Stiven | |
| dc.coverage.temporal | Feb 2024 - Jun 2024 | |
| dc.date.accessioned | 2024-10-17T13:21:20Z | |
| dc.date.available | 2024-10-17T13:21:20Z | |
| dc.date.issued | 2024-07-05 | |
| dc.identifier.uri | http://hdl.handle.net/10823/7382 | |
| dc.description.abstract | En el presente documento se hace una propuesta de solución a problemáticas relacionadas con la dificultad en la comprensión, falta de conocimiento y acceso a los reglamentos institucionales por parte de la comunidad estudiantil del Politécnico Grancolombiano. La existencia de esta situación se corroboró mediante una encuesta a miembros de la comunidad académica, en la cual se evidenció un bajo nivel de familiaridad con las normas y una percepción negativa hacia ellas. Para abordar esta problemática se desarrolló una aplicación web de asesoramiento normativo utilizando inteligencia artificial. Esta aplicación permite a los usuarios obtener respuestas relacionadas con situaciones o preguntas específicas y provee un acceso a la información actualizada del reglamento académico. Para el desarrollo se utilizaron técnicas de procesamiento de lenguaje natural (PLN) y clasificación de texto con redes neuronales, aprovechando modelos de lenguaje grandes (LLM) como BERT. Se realizó un proceso de selección y entrenamiento de la herramienta con información relacionada con el reglamento académico, para construir módulos que permitan manejar y presentar dicha información. Se espera que la aplicación mejore el acceso y comprensión de las normas institucionales, empoderando a los estudiantes para resolver sus dudas de manera autónoma y eficiente, lo cual no solo optimizará los recursos institucionales, sino que también fomentará una cultura educativa más colaborativa y autónoma. Para evaluar el funcionamiento de la aplicación se utilizó un instrumento de recolección de información con un grupo de estudiantes, quienes probaron la herramienta y evaluaron criterios como usabilidad, rendimiento y precisión. | spa |
| dc.description.tableofcontents | Índice Resumen del Proyecto... 6 TITULO DE LA PROPUESTA... 7 INTRODUCCIÓN... 8 PLANTEAMIENTO DEL PROBLEMA... 10 OBJETIVOS... 11 Objetivos específicos... 11 JUSTIFICACIÓN... 12 ALCANCE... 13 MARCO TEÓRICO... 14 Marco Teórico... 14 Estado del Arte... 16 METODOLOGÍA... 22 Análisis preliminar... 22 Árbol de problemas... 22 Encuestas... 23 Definición de tecnologías... 24 Actividades y cronograma... 25 Diseño de la solución ... 27 Requerimientos... 27 Casos de uso... 28 Arquitectura... 28 Base de datos... 29 Diseño de interfaz... 31 Desarrollo de la solución... 31 Prototipado y experimentación... 31 Entrenamiento e implementación de modelo... 37 Desarrollo de módulo de procesamiento de texto... 40 Desarrollo de backend... 41 Desarrollo de frontend... 42 Pruebas y finalización... 45 RESULTADOS... 46 Conclusiones... 48 Trabajo futuro... 49 BIBLIOGRAFÍA... 50 ANEXOS... 53 | spa |
| dc.format.mimetype | application/pdf | spa |
| dc.language.iso | spa | spa |
| dc.title | Desarrollo de un asesor normativo mediante inteligencia artificial para el reglamento estudiantil del Politécnico Grancolombiano | spa |
| dc.type | bachelorThesis | spa |
| dc.type.local | Tesis/Trabajo de grado - Monografía - Pregrado | spa |
| dc.type.driver | info:eu-repo/semantics/bachelorThesis | spa |
| dc.title.translated | Development of a regulatory advisor using artificial intelligence for the student regulations of Politécnico Grancolombiano | spa |
| dc.subject.proposal | Asesor normativo | spa |
| dc.subject.proposal | LLM | spa |
| dc.subject.proposal | Procesamiento de lenguaje natural | spa |
| dc.subject.proposal | Redes neuronales | spa |
| dc.subject.lemb | Inteligencia artificial | spa |
| dc.subject.lemb | Procesamiento de datos | spa |
| dc.subject.lemb | Reglamentación académica | spa |
| dc.description.abstractenglish | In this document, a proposed solution is presented to address issues related to the difficulty in understanding, lack of knowledge, and limited access to institutional regulations by the student community of Politécnico Grancolombiano. The existence of this situation was confirmed through a survey conducted among members of the academic community, which revealed a low level of familiarity with the regulations and a negative perception of them. To tackle this issue, a web-based regulatory advisory application was developed using artificial intelligence. This application allows users to obtain answers related to specific situations or questions and provides access to updated information from the academic regulations. The development process utilized natural language processing (NLP) techniques and text classification with neural networks, leveraging large language models (LLMs) such as BERT. A selection and training process was conducted with information related to the academic regulations to build modules that manage and present this information effectively. The application is expected to improve access to and understanding of institutional regulations, empowering students to resolve their queries independently and efficiently. This will not only optimize institutional resources but also promote a more collaborative and autonomous educational culture. To assess the functionality of the application, an information collection tool was used with a group of students, who tested the tool and evaluated criteria such as usability, performance, and accuracy. | spa |
| dc.subject.keywords | LLM | spa |
| dc.subject.keywords | Natural language processing | spa |
| dc.subject.keywords | Neural networks | spa |
| dc.subject.keywords | Regulatory advisor | spa |
| dc.relation.references | Nataraj, P., Devaraj, Teja, R., Kumar, M., & Gangrade, A. (2023). Development of a Legal Document AI-Chatbot. ArXiv, abs/2311.12719. | spa |
| dc.relation.references | Queudot, M., Charton, E., & Meurs, M. (2020). Improving Access to Justice with Legal Chatbots. Stats. | spa |
| dc.relation.references | Cui, J., Li, Z., Yan, Y., Chen, B., & Yuan, L. (2023). Chatlaw: A Multi-Agent Collaborative Legal Assistant with Knowledge Graph Enhanced Mixture-of- Experts Large Language Model. | spa |
| dc.relation.references | Han, H. (2023). Potential Benefits of Employing Large Language Models in Research in Moral Education and Development. ArXiv, abs/2306.13805. | spa |
| dc.relation.references | Morgan, J., Paiement, A., Seisenberger, M., Williams, J., & Wyner, A.Z. (2018). A Chatbot Framework for the Children's Legal Centre. International Conference on Legal Knowledge and Information Systems. | spa |
| dc.relation.references | Ng, J., Haller, E., & Murray, A. (2022). The ethical chatbot: A viable solution to socio-legal issues. Alternative Law Journal, 47, 308 - 313. https://doi.org/10.1177/1037969X221113598. https://researchers.cdu.edu.au/en/publications/the-ethical-chatbot-a-viablesolution- to-socio-legal-issues | spa |
| dc.relation.references | Devlin, J., Chang, M., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. North American Chapter of the Association for Computational Linguistics. | spa |
| dc.relation.references | Abdulwahhab, R., Makhmari, H., & Battashi, S. (2015). An educational web application for academic advising. 2015 IEEE 8th GCC Conference & Exhibition, 1-6. https://doi.org/10.1109/IEEEGCC.2015.7060084. | spa |
| dc.relation.references | Aly, W., Eskaf, K., & Selim, A. (2017). Fuzzy mobile expert system for academic advising. 2017 IEEE 30th Canadian Conference on Electrical and Computer Engineering (CCECE), 1-5. https://doi.org/10.1109/CCECE.2017.7946846. | spa |
| dc.relation.references | Arsys (2020) Clasificación de textos con Python y Jupyter Notebooks [Código fuente]. Arsys https://www.arsys.es/blog/clasificaciontextos-pythonjupyternotebooks | spa |
| dc.relation.references | Church, K.W., Chen, Z., & Ma, Y. (2021). Emerging trends: A gentle introduction to fine-tuning. Natural Language Engineering, 27, 763 - 778. | spa |
| dc.relation.references | Naveed, H., Khan, A.U., Qiu, S., Saqib, M., Anwar, S., Usman, M., Barnes, N., & Mian, A.S. (2023). A Comprehensive Overview of Large Language Models. ArXiv, abs/2307.06435. | spa |
| dc.relation.references | Mannadiar, N., & Gürsoy, K. (2019). Neural Networks for Text Classification. | spa |
| dc.relation.references | Minaee, S., Kalchbrenner, N., Cambria, E., Nikzad, N., Chenaghlu, M., & Gao, J. (2020). Deep Learning--based Text Classification. ACM Computing Surveys (CSUR), 54, 1 - 40. | spa |
| dc.relation.references | Попова, Е., Popova, E., Спицын, В., Spicyn, V., Иванова, Ю., & Ivanova, Y. (2019). Using artificial neural networks to solve text classification problems. GraphiCon'2019 Proceedings. Volume 1. | spa |
| dc.relation.references | Sun, Z. (2023). A Short Survey of Viewing Large Language Models in Legal Aspect. ArXiv, abs/2303.09136. | spa |
| dc.relation.references | Hmeidi, I., Al-Ayyoub, M., Abdulla, N., Almodawar, A., Abooraig, R., & Mahyoub, N. (2015). Automatic Arabic text categorization: A comprehensive comparative study. Journal of Information Science, 41, 114 - 124. | spa |
| dc.relation.references | Zhang, X., Zhao, J.J., & LeCun, Y. (2015). Character-level Convolutional Networks for Text Classification. Neural Information Processing Systems. | spa |
| dc.relation.references | Liddy, E.D., Paik, W., & Yu, E.S. (1994). Text categorization for multiple users based on semantic features from a machine-readable dictionary. ACM Trans. Inf. Syst., 12, 278-295. | spa |
| dc.relation.references | Kamruzzaman, S. (2010). Text Classification using Artificial Intelligence. ArXiv, abs/1009.4964. | spa |
| dc.relation.references | Howard, J., & Ruder, S. (2018). Universal Language Model Fine-tuning for Text Classification. Annual Meeting of the Association for Computational Linguistics. | spa |
| dc.relation.references | Qasem, R., Tantour, B., & Maree, M. (2023). Towards the Exploitation of LLMbased Chatbot for Providing Legal Support to Palestinian Cooperatives. ArXiv, abs/2306.05827. https://www.mckinsey.com/capabilities/quantumblack/our-insights/globalsurvey- the-state-of-ai-in-2020?cid=other-soc-lkn-mip-mck-oth--- &sid=4255306818&linkId=105722332 | spa |
| dc.relation.references | Minaee, S., Cambria, E., & Gao, J. (2020). Deep Learning--based Text Classification. ACM Computing Surveys (CSUR), 54, 1 - 40. | spa |
| dc.relation.references | Dande, A.A., & Pund, D.M. (2023). A Review Study on Applications of Natural Language Processing. International Journal of Scientific Research in Science, Engineering and Technology. | spa |
| dc.relation.references | Vanita (2024). An Extant of Natural Language Processing. International Journal For Multidisciplinary Research. | spa |
| dc.relation.references | Yadav, R.K., Madaan, A., & Janu (2024). Comprehensive analysis of natural language processing. Global Journal of Engineering and Technology Advances. | spa |
| dc.relation.references | Cambria, E., & White, B. (2014). Jumping NLP Curves: A Review of Natural Language Processing Research [Review Article]. IEEE Computational Intelligence Magazine, 9, 48-57. | spa |
| dc.relation.references | G. Suganya, R. Porkodi (2020). Prediction and Analysis of Extracting Relations using Spacy Model. International Journal of Recent Technology and Engineering. | spa |
| dc.relation.references | Yao, L., Mao, C., & Luo, Y. (2018). Graph Convolutional Networks for Text Classification. ArXiv, abs/1809.05679. | spa |
| dc.relation.references | Delaforge, A., Azé, J., Bringay, S., Mollevi, C., Sallaberry, A., & Servajean, M. (2022). EBBE-Text: Explaining Neural Networks by Exploring Text Classification Decision Boundaries. IEEE Transactions on Visualization and Computer Graphics, 29, 4154-4171. | spa |
| dc.relation.references | Gutiérrez, F., Seipp, K., Ochoa, X., Chiluiza, K., Laet, T.D., & Verbert, K. (2020). LADA: A learning analytics dashboard for academic advising. Comput. Hum. Behav., 107, 105826 | spa |
| dc.relation.references | Alkhoori, A., Kuhail, M.A., & Alkhoori, A. (2020). UniBud: A Virtual Academic Adviser. 2020 12th Annual Undergraduate Research Conference on Applied Computing (URC), 1-4 | spa |
| dc.publisher.program | Ingeniería de Sistemas | spa |
| dc.type.coar | http://purl.org/coar/resource_type/c_7a1f | spa |
| dc.publisher.faculty | Facultad de ingeniería y Diseño e Innovación | spa |
| dc.identifier.instname | instname:Politécnico Grancolombiano | spa |
| dc.identifier.reponame | reponame:Alejandría Repositorio Comunidad | spa |
| dc.type.hasversion | info:eu-repo/semantics/acceptedVersion | |
| dc.rights.accessrights | info:eu-repo/semantics/openAccess | |
| dc.identifier.repourl | repourl:http://alejandria.poligran.edu.co | spa |
| dc.type.redcol | https://purl.org/redcol/resource_type/TP | |
| dc.rights.creativecommons | Atribución-NoComercial-SinDerivadas 2.5 Colombia | spa |
| dc.type.version | info:eu-repo/semantics/acceptedVersion | spa |