dc.contributor.advisor | Khriyenko, Oleksiy | |
dc.contributor.author | Yadav, Bhanu Pratap | |
dc.date.accessioned | 2024-05-31T06:19:24Z | |
dc.date.available | 2024-05-31T06:19:24Z | |
dc.date.issued | 2024 | |
dc.identifier.uri | https://jyx.jyu.fi/handle/123456789/95394 | |
dc.description.abstract | Software testing is an important part of the software development life cycle (SLDC). In order to meet the requirements of software functionality, quality, and reliability, different kinds of testing are carried out during the development, deployment, and maintenance phases of the software. Testing processing can be carried out manually or automatically using automation scripts and tools. Currently, the major problems in software testing are time-consuming, and in cases of manual testing, error-proneness and cost add up to more challenges. In agile software development, testers need to analyse the requirements of the user stories in detail, and write test cases for the user stories. One user story might have multiple test cases, creating them manually requires a lot of time and effort. In recent years, Natural Language Processing(NLP) has made significant progress in understanding the meaning and context of human-understandable words and languages. The Transformer, a kind of NLP model, is able to perform a wide range of NLP related tasks with maximum accuracy. The purpose of this research is to understand and analyse the feasibility of using natural process language to generate software test cases automatically from user stories. By understanding user stories and converting them into appropriate test cases through the help of fine tuned T5 model, this research aims to decrease the time and effort needed to create test cases manually and improve the overall efficiency and accuracy of the software testing process. The research includes the study of transformer architecture, which is a deep learning model for natural language processing. Preparing custom datasets, preprocessing them, fine-tuning the T5 model on the prepared dataset, and finally assessing the model's performance using Recall-Oriented Understudy for Gisting Evaluation (ROUGE), a Natural Language Generation (NLG) assessment metric, are all included in the experiment section. | en |
dc.format.extent | 55 | |
dc.format.mimetype | application/pdf | |
dc.language.iso | eng | |
dc.rights | In copyright | |
dc.title | Automating test case generation based on user story using natural language processing to increase software testing efficiency | |
dc.type | master thesis | |
dc.identifier.urn | URN:NBN:fi:jyu-202405314157 | |
dc.contributor.tiedekunta | Faculty of Information Technology | en |
dc.contributor.tiedekunta | Informaatioteknologian tiedekunta | fi |
dc.contributor.yliopisto | Jyväskylän yliopisto | fi |
dc.contributor.yliopisto | University of Jyväskylä | en |
dc.contributor.oppiaine | Cognitive Computing and Collective Intelligence | en |
dc.type.coar | http://purl.org/coar/resource_type/c_bdcc | |
dc.rights.copyright | © The Author(s) | |
dc.rights.accesslevel | restrictedAccess | |
dc.type.publication | masterThesis | |
dc.format.content | fulltext | |
dc.rights.url | https://rightsstatements.org/page/InC/1.0/ | |
dc.rights.accessrights | The author has not given permission to make the work publicly available electronically. Therefore the material can be read only at the archival workstation at Jyväskylä University Library (https://kirjasto.jyu.fi/en/workspaces/facilities/facilities#autotoc-item-autotoc-2). | en |
dc.rights.accessrights | Tekijä ei ole antanut lupaa avoimeen julkaisuun, joten aineisto on luettavissa vain Jyväskylän yliopiston kirjaston arkistotyösemalta. Ks. https://kirjasto.jyu.fi/fi/tyoskentelytilat/laitteet-ja-tilat#autotoc-item-autotoc-2. | fi |