Designing a Conversational Requirements Elicitation System for End-Users

Context: Digital transformation impacts an ever-increasing degree of everyone's business and private life. It is imperative to incorporate a wide audience of user requirements in the development process to design successful information systems (IS). Hence, requirements elicitation (RE) is increasingly performed by end-users that are novices at contributing requirements to IS development projects. Objective: We need to develop RE systems that are capable of assisting a wide audience of end-users in communicating their needs and requirements. Prominent methods, such as elicitation interviews, are challenging to apply in such a context, as time and location constraints limit potential audiences. Research Method: The presented dissertation project utilizes design science research to develop a requirements self-elicitation system, LadderBot. A conversational agent (CA) enables end-users to articulate needs and requirements on the grounds of the laddering method. The CA mimics a human interviewer's capability to rephrase questions and provide assistance in the process and allows users to converse in their natural language. Furthermore, the tool will assist requirements analysts with the subsequent aggregation and analysis of collected data. Contribution: The dissertation project makes a practical contribution in the form of a ready-to-use system for wide audience end-user RE and subsequent analysis utilizing laddering as cognitive elicitation technique. A theoretical contribution is provided by developing a design theory for the application of conversational agents for RE, including the laboratory and field evaluation of design principles.