Högskolan i Skövde

his.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Evaluating Artificial Short Message Service Campaigns through Rule Based Multi-instance Multi-label Classification
University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment. University of Borås, Sweden.ORCID iD: 0000-0002-3553-5983
University of Borås, Sweden.ORCID iD: 0000-0003-4308-434X
University of Borås, Sweden.ORCID iD: 0000-0002-5814-9604
University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment. (Informationssystem (IS), Information Systems)ORCID iD: 0000-0002-8900-6139
2021 (English)In: Proceedings of the AAAI 2021 Spring Symposium on Combining Machine Learning and Knowledge Engineering (AAAI-MAKE 2021): Stanford University, Palo Alto, California, USA, March 22-24, 2021 / [ed] A. Martin; K. Hinkelmann; H.-G. Fill; A. Gerber D. Lenat; R. Stolle; F. van Harmelen, CEUR-WS , 2021, Vol. 2846Conference paper, Published paper (Refereed)
Abstract [en]

Marketers need new ways of generating campaigns artificially for their marketing activities. Many marketers assume proprietary systems are individualized enough. This article investigates an order of models used to measure how reliably a system can generate campaigns artificially while producing a campaign classification and generation models that are integrated into an intelligent marketing system. The order is between a Classification Model (CM) and a Generation Model (GM). The order also functions as an iterative model improvement process for developing the models by evaluating the models’ accuracy distributions. The CM received a mean accuracy of 100%. The GM received 98.9% mean accuracy and a reproducibility score of 96.2%, implying the vast potential for increased resource savings, marketing precision, and less consumer annoyance. The conclusion is that the developed system can reliantly construct campaigns

Place, publisher, year, edition, pages
CEUR-WS , 2021. Vol. 2846
Series
CEUR Workshop Proceedings, ISSN 1613-0073 ; 2846
Keywords [en]
Artificial intelligence, Intelligent marketing system, Iterative model improvement
National Category
Engineering and Technology Computer and Information Sciences Computer Sciences
Research subject
Information Systems
Identifiers
URN: urn:nbn:se:his:diva-19604Scopus ID: 2-s2.0-85104648031OAI: oai:DiVA.org:his-19604DiVA, id: diva2:1543413
Conference
AAAI 2021 Spring Symposium on Combining Machine Learning and Knowledge Engineering (AAAI-MAKE 2021), Stanford University, Palo Alto, California, USA, March 22-24, 2021
Funder
Knowledge Foundation, 20160035, 20170215
Note

CC BY 4.0

CEUR Workshop Proceedings (CEUR-WS.org) is a free open-access publication service at Sun SITE Central Europe

Available from: 2021-04-12 Created: 2021-04-12 Last updated: 2023-09-21Bibliographically approved
In thesis
1. Designing Advertisement Systems with Human-centered Artificial Intelligence
Open this publication in new window or tab >>Designing Advertisement Systems with Human-centered Artificial Intelligence
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.

Available from: 2023-10-02 Created: 2023-09-21 Last updated: 2023-10-03Bibliographically approved

Open Access in DiVA

fulltext(1452 kB)91 downloads
File information
File name FULLTEXT01.pdfFile size 1452 kBChecksum SHA-512
4157efe12e2695345668852cbaf69923d7a35fb6bbd24c1d8d933a4bba6eb2278d4606d323cff4f38e5ebf4976de150a9b072062dba17f10380b34b997bbba0c
Type fulltextMimetype application/pdf

Other links

ScopusFulltext (proceedings)Fulltext (PDF)

Authority records

Sahlin, JohannesHolgersson, Jesper

Search in DiVA

By author/editor
Sahlin, JohannesSundell, HåkanAlm, HåkanHolgersson, Jesper
By organisation
School of InformaticsInformatics Research Environment
Engineering and TechnologyComputer and Information SciencesComputer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 91 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 171 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf