The success of software development projects heavily depends on effectively capturing and meeting stakeholders' requirements. However, involving multiple stakeholders with diverse backgrounds and objectives often leads to conflicts among these requirements. These conflicts represent inconsistencies in the system design, resulting in various challenges, including project delays, increased costs, and potential system failures. Previous research has primarily focused on identifying conflicts with algorithms or negotiation, while conversational AI's potential to detect conflicts in real-time has been neglected. This thesis study addresses the challenge of requirement conflicts by proposing a novel approach that leverages conversational AI in the form of a chatbot. The chatbot, developed using the Rasa platform, enables real-time detection of conflicts, focusing on three general types: duplicated (similar), incompatible, and contradictory requirements. During the study, the design science research method is employed to guide the chatbot's development. Further, an experiment is applied to evaluate the chatbot's performance compared with domain experts using four different datasets. The experiment results are presented using F1 scores, which calculate precision and recall for both the chatbot and the experts on each dataset. Overall, the chatbot scored 0.8, while the experts achieved a slightly higher score of 0.86. To determine if there was a statistically significant difference between the two performances, a Wilcoxon signed-rank test was conducted on the results. The analysis showed no significant difference in the F1 score between the chatbot and the experts, indicating the chatbot's feasibility and effectiveness in detecting conflicts. The contribution of this thesis study can advance requirements engineering by providing a user-friendly and efficient method for real-time conflict detection, enhancing the quality and overall success of software development projects.

Studien består av en jämförelse av det traditionella arbetssättet,vattenfallsmodellen, och den agila modellen. Studiens fokus ligger påatt undersöka skillnaderna som finns mellan modellerna när detkommer till kravhanteringen och hur man arbetar med att uppfyllakraven. Fokus ligger också på att undersöka varför vissa projektföredrar att arbeta efter vattenfallsmodellen, istället för att använda denagila modellen.Undersökningen består av en litteraturförstudie och semistruktureradeintervjuer med personer som har erfarenhet av båda modellerna.Resultatet av de semistrukturerade intervjuerna sammanställs ochjämförs med resultatet från undersökningen, detta för att kunna besvarafrågeställningarna.Resultatet visar att de skiljer sig markant i kravhanteringen och hur manarbetar med att uppfylla kraven i det olika modellerna.Detta bidrar till att det skiljer sig mycket vilken modell som föredras.Ett exempel som kom fram under intervjuerna är att inom vissa delar avmedicinbranschen så krävs det ett omfattade förarbete då det är olikalagar i olika länder.Det visa sig att statliga och privata verksamheter inte spelar in i valet avmodell utan att det som avgör vilken modell som föredras är vilken typav projekt. Vilken typ av miljö som projektet utförs i spelar också en storroll.Vattenfallsmodellen föredras i projekt som styrs av lagar och regelverkeller om det är väldigt specifika krav. Agila modellen föredras då det ärfriare projekt där lagar och regler inte måste tas i hänsyn på samma sätt. / The study consists of a comparison on the traditional way of working,the waterfall model, and the agile model. The focus of the study is toexamine the differences that exist between the models when it comes torequirements management and how to work to meet the requirements.The focus will also be on examine why some projects prefer to workaccording to the waterfall model, instead of switching to the agilemodel.The survey consists of a literature pre-study and semi-structuredinterviews with people who have experience of both models. The resultsthat where collected from the semi-structured interviews have beencompiled and compared whit the results which were collected from thesurvey in order to be able to answer the questions.The results show that they differ markedly in the requirementsmanagement and how to work with meeting the requirements in thedifferent models. This contributes to the fact that there is a lot ofdifference in which model that is preferred. An example that emergedduring the interviews was that in certain parts of the medical industry,extensive preparatory work is required as there are different laws indifferent countries.It turned out that government and private activities do not play a role inthe choice of model, but that what determines which model is preferredis the type of project. The type of environment in which the projectconsists also plays a major role.The waterfall model will be preferred in projects governed by laws andregulations or if there are very specific requirements. The agile model ispreferred when the projects is freer and where laws and regulations donot have to be taken into account in the same way.