Open this publication in new window or tab >>2023 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]
Practitioners are urging using Artificial Intelligence (AI) to improve advertisements. Advertisers recognize the importance of incorporating AI into their strategies to remain competitive. In response to this demand, a Design Science Research (DSR) initiative has been started to create a Human-Centered AI (HCAI) tool to enhance advertisement suggestions by analyzing consumer behavior. This dissertation aims to build an advertisement optimization system with HCAI and produce an Information System Design Theory (ISDT) of that class of system. Through architectural models, methods, technological rules, and design principles, nascent Design Theory (DT) is created and serves as an initial stage towards achieving a more abstract design knowledge known as the ISDT. The action design research method is employed to construct and analyze the implemented system instance. The process involves multiple cycles of building, intervening, and evaluating. These cycles are conducted iteratively and incrementally, allowing for the gradual development of the suggested system while simultaneously generating valuable design knowledge. The system is developed and abstracted for design knowledge from both the development process and the actual tool. The dissertation presents nascent design knowledge in the form of models, technological rules, and design principles. Moreover, the dissertation places the nascent DT within the broader context of a more abstract design knowledge called ISDT. The results are then scrutinized based on various components of the DT, including purpose and scope, constructs, principles of form and function, artifact mutability, justificatory knowledge, testable propositions, principles of implementation, and expository instantiation. This dissertation discusses the DSR process, compared to various challenges encountered throughout the research project. Theoretical, empirical, and artefactual research contributions are outlined, and their implications for research and practice are discussed toward the end of the dissertation. The quality of the research is examined, considering the relevance, novelty, usefulness, feasibility, design rigor, evaluation rigor, and transparency of the artifacts produced throughout the dissertation. The dissertation concludes that it delivered ISDT. Moreover, the system serves as a valuable example of how AI can be utilized for optimizing digital advertisements. The dissertation ends with providing recommendations for future research.
Place, publisher, year, edition, pages
Skövde: University of Skövde, 2023. p. xiv, 361
Series
Dissertation Series ; 54
Keywords
Digital Advertisement Optimization, Design Knowledge, Information System Design Theory, Artificial Intelligence, Reinforcement Learning, Human-centered AI
National Category
Computer Sciences
Identifiers
urn:nbn:se:his:diva-23234 (URN)978-91-987906-8-9 (ISBN)
Public defence
2023-11-01, Insikten, Kanikegränd 3B, Skövde, 10:00
Opponent
Supervisors
Funder
Knowledge Foundation, 20160035, 20170215
Note
Partly funded by The Knowledge Foundation, grants nr. 20160035, 20170215
Två av sex delarbeten (övriga se rubriken Delarbeten/List of papers):
Sahlin, Johannes, Håkan Sundell, Gideon Mbiydzenyuy, and Jesper Holgersson (2023). “Managing Consumer Concerns of Model-generated Advertisements.” In: Expert Systems with Applications, Submitted.
— (2024). “Nascent Design Theory for Advertisement Optimization Systems with Human-centered Artificial Intelligence.” In: European Conference on Information Systems, Draft.
2023-10-022023-09-212023-10-03Bibliographically approved