{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"id":[{"id":"https:\/\/ror.org\/03mb6wj31","id-type":"ROR","asserted-by":"publisher"},{"id":"https:\/\/www.isni.org\/000000041937028X","id-type":"ISNI","asserted-by":"publisher"},{"id":"https:\/\/www.wikidata.org\/entity\/Q1640731","id-type":"wikidata","asserted-by":"publisher"}],"name":"Universitat Polit\u00e8cnica de Catalunya","acronym":["UPC"]}],"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:18:09Z","timestamp":1768853889259,"version":"3.49.0"},"reference-count":0,"publisher":"Universitat Polit\u00e8cnica de Catalunya","license":[{"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>(English) Requirements engineering (RE) is fundamental to successful software development, especially in modern, large-scale projects. Efficient management of text-based artefacts is key to accurate elicitation, refinement, and validation of requirements. Despite the industrial trend towards adopting natural language processing (NLP) methods, challenges in their pervasiveness, reliability, scalability, and reusability persist. Moreover, the advent of large language models (LLMs) has set the groundwork for further research in automated document analysis in the field of RE.\r\n\r\nThis thesis explores the integration of NLP methods and tools to automate and enhance RE tasks (NLP4RE) in three document-oriented areas: requirements traceability, requirements analysis for information retrieval, and requirements feedback gathering. For requirements traceability, methods for dependency and duplicate detection in text-based requirements documents are proposed and evaluated. In requirements analysis, a knowledge graph-based approach is developed to create adaptive, crowdsourced repositories of RE-related documents. For requirements feedback gathering, techniques for extracting features from user reviews and analyzing feedback are presented and evaluated.\r\n\r\nThis research is shaped in the context of multiple case and sample studies validated empirically, demonstrating their effectiveness in real-world scenarios. The contributions presented in this thesis entail advancements in streamlining RE tasks and improving the accuracy, efficiency and adoption of NLP4RE tools and methods. Ultimately, this thesis aims to provide novel insights, methodologies and technical contributions to the NLP4RE field.<\/jats:p>\n                <jats:p>(Catal\u00e0) L'enginyeria de requisits (RE) \u00e9s fonamental per a l'\u00e8xit del desenvolupament de programari, especialment en projectes moderns i de gran escala. La gesti\u00f3 eficient dels documents de text generats durant aquesta fase \u00e9s clau per a la correcta obtenci\u00f3, refinament i validaci\u00f3 dels requisits. Tot i la tend\u00e8ncia industrial cap a l'adopci\u00f3 de m\u00e8todes de processament del llenguatge natural (NLP), encara persisteixen diversos reptes relacionats amb la seva pres\u00e8ncia, fiabilitat, escalabilitat i reutilitzaci\u00f3. A m\u00e9s, l'aparici\u00f3 de grans models de llenguatge (LLMs) ha establert les bases per a una recerca dedicada a l'an\u00e0lisi autom\u00e0tica de documents en el camp de la RE.\r\n\r\nAquesta tesi explora la integraci\u00f3 de m\u00e8todes i eines de NLP per automatitzar i millorar les tasques de RE (NLP4RE) en tres \u00e0rees orientades a documents: tra\u00e7abilitat de requisits, an\u00e0lisi i recuperaci\u00f3 d'informaci\u00f3 de requisits, i recollida de retroalimentaci\u00f3 sobre els requisits. Per a la tra\u00e7abilitat de requisits, es proposen i s'avaluen m\u00e8todes per a la detecci\u00f3 de depend\u00e8ncies i duplicats en documents de requisits basats en text. En l'an\u00e0lisi de requisits, es proposa un desenvolupament basat en grafs de coneixement per crear repositoris adaptables de documents de prove\u00efment participatiu relacionats amb la RE. Per a la recollida de retroalimentaci\u00f3, es presenten t\u00e8cniques per extreure caracter\u00edstiques i funcionalitats dels comentaris dels usuaris i analitzar-los.\r\n\r\nAquesta investigaci\u00f3 es basa en m\u00faltiples casos d'estudi validats emp\u00edricament, demostrant la seva efectivitat en escenaris del m\u00f3n real. Les contribucions presentades en aquesta tesi inclouen aven\u00e7os en l'automatitzaci\u00f3 de tasques de RE i la millora de l'exactitud, l'efici\u00e8ncia i l'adopci\u00f3 d'eines i m\u00e8todes en el camp de NLP4RE. En definitiva, aquesta tesi pret\u00e9n oferir noves perspectives, metodologies i contribucions t\u00e8cniques al camp de NLP4RE.<\/jats:p>\n                <jats:p>(Espa\u00f1ol) La ingenier\u00eda de requisitos (RE) es fundamental para el desarrollo exitoso de software, especialmente en proyectos modernos a gran escala. La gesti\u00f3n eficiente de artefactos basados en texto es clave para la correcta obtenci\u00f3n, refinamiento y validaci\u00f3n de los requisitos. A pesar de la tendencia industrial hacia la adopci\u00f3n de m\u00e9todos de procesamiento de lenguaje natural (NLP), persisten desaf\u00edos en cuanto a su adopci\u00f3n, fiabilidad, escalabilidad y reutilizaci\u00f3n. Adem\u00e1s, la aparici\u00f3n de grandes modelos de lenguaje (LLMs) ha sentado las bases para futuras investigaciones en an\u00e1lisis automatizado de documentos en el campo de la RE.\r\n\r\nEsta tesis explora la integraci\u00f3n de m\u00e9todos y herramientas de NLP para automatizar y mejorar las tareas de RE (NLP4RE) en tres \u00e1reas orientadas a documentos: trazabilidad de requisitos, an\u00e1lisis de requisitos para la recuperaci\u00f3n de informaci\u00f3n y recopilaci\u00f3n de retroalimentaci\u00f3n de requisitos. Para la trazabilidad de requisitos, se proponen y eval\u00faan m\u00e9todos para la detecci\u00f3n de dependencias y duplicados en documentos de requisitos basados en texto. En el an\u00e1lisis de requisitos, se desarrolla un enfoque basado en grafos de conocimiento para crear repositorios adaptativos y colaborativos de documentos relacionados con RE. Para la recopilaci\u00f3n de retroalimentaci\u00f3n de requisitos, se presentan y eval\u00faan t\u00e9cnicas para la extracci\u00f3n de caracter\u00edsticas de rese\u00f1as de usuarios y el an\u00e1lisis de dicha retroalimentaci\u00f3n.\r\n\r\nEsta investigaci\u00f3n se enmarca en el contexto de m\u00faltiples casos de estudio y estudios de muestra validados emp\u00edricamente, demostrando su efectividad en escenarios del mundo real. Las contribuciones presentadas en esta tesis implican avances en la optimizaci\u00f3n de las tareas de RE y la mejora en la precisi\u00f3n, eficiencia y adopci\u00f3n de herramientas y m\u00e9todos NLP4RE. En \u00faltima instancia, esta tesis tiene como objetivo proporcionar nuevas perspectivas, metodolog\u00edas y contribuciones t\u00e9cnicas al campo de NLP4RE.<\/jats:p>","DOI":"10.5821\/dissertation-2117-417795","type":"dissertation","created":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T01:22:31Z","timestamp":1731633751000},"approved":{"date-parts":[[2024,11,4]]},"source":"Crossref","is-referenced-by-count":1,"title":["Natural language processing methods for document-based requirements specification and validation tasks"],"prefix":"10.5821","author":[{"sequence":"additional","affiliation":[]},{"given":"Joaquim","family":"Motger de la Encarnaci\u00f3n","sequence":"first","affiliation":[]}],"member":"3865","container-title":[],"original-title":[],"deposited":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T06:36:29Z","timestamp":1768804589000},"score":1,"resource":{"primary":{"URL":"https:\/\/hdl.handle.net\/2117\/417795"}},"subtitle":[],"editor":[{"given":"Javier","family":"Franch Guti\u00e9rrez","sequence":"first","affiliation":[]},{"given":"Jordi","family":"Marco G\u00f3mez","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":0,"URL":"https:\/\/doi.org\/10.5821\/dissertation-2117-417795","relation":{},"subject":[]}}