Högskolan i Skövde

his.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Evaluating Artificial Short Message Service Campaigns through Rule Based Multi-instance Multi-label Classification
Högskolan i Skövde, Institutionen för informationsteknologi. Högskolan i Skövde, Forskningsmiljön Informationsteknologi. 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
Högskolan i Skövde, Institutionen för informationsteknologi. Högskolan i Skövde, Forskningsmiljön Informationsteknologi. (Informationssystem (IS), Information Systems)ORCID-id: 0000-0002-8900-6139
2021 (engelsk)Inngår i: 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. 2846Konferansepaper, Publicerat paper (Fagfellevurdert)
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

sted, utgiver, år, opplag, sider
CEUR-WS , 2021. Vol. 2846
Serie
CEUR Workshop Proceedings, ISSN 1613-0073 ; 2846
Emneord [en]
Artificial intelligence, Intelligent marketing system, Iterative model improvement
HSV kategori
Forskningsprogram
Informationssystem (IS)
Identifikatorer
URN: urn:nbn:se:his:diva-19604Scopus ID: 2-s2.0-85104648031OAI: oai:DiVA.org:his-19604DiVA, id: diva2:1543413
Konferanse
AAAI 2021 Spring Symposium on Combining Machine Learning and Knowledge Engineering (AAAI-MAKE 2021), Stanford University, Palo Alto, California, USA, March 22-24, 2021
Forskningsfinansiär
Knowledge Foundation, 20160035, 20170215
Merknad

CC BY 4.0

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

Tilgjengelig fra: 2021-04-12 Laget: 2021-04-12 Sist oppdatert: 2023-09-21bibliografisk kontrollert
Inngår i avhandling
1. Designing Advertisement Systems with Human-centered Artificial Intelligence
Åpne denne publikasjonen i ny fane eller vindu >>Designing Advertisement Systems with Human-centered Artificial Intelligence
2023 (engelsk)Doktoravhandling, med artikler (Annet vitenskapelig)
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.

sted, utgiver, år, opplag, sider
Skövde: University of Skövde, 2023. s. xiv, 361
Serie
Dissertation Series ; 54
Emneord
Digital Advertisement Optimization, Design Knowledge, Information System Design Theory, Artificial Intelligence, Reinforcement Learning, Human-centered AI
HSV kategori
Identifikatorer
urn:nbn:se:his:diva-23234 (URN)978-91-987906-8-9 (ISBN)
Disputas
2023-11-01, Insikten, Kanikegränd 3B, Skövde, 10:00
Opponent
Veileder
Forskningsfinansiär
Knowledge Foundation, 20160035, 20170215
Merknad

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.

Tilgjengelig fra: 2023-10-02 Laget: 2023-09-21 Sist oppdatert: 2023-10-03bibliografisk kontrollert

Open Access i DiVA

fulltext(1452 kB)90 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 1452 kBChecksum SHA-512
4157efe12e2695345668852cbaf69923d7a35fb6bbd24c1d8d933a4bba6eb2278d4606d323cff4f38e5ebf4976de150a9b072062dba17f10380b34b997bbba0c
Type fulltextMimetype application/pdf

Andre lenker

ScopusFulltext (proceedings)Fulltext (PDF)

Person

Sahlin, JohannesHolgersson, Jesper

Søk i DiVA

Av forfatter/redaktør
Sahlin, JohannesSundell, HåkanAlm, HåkanHolgersson, Jesper
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 90 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

urn-nbn

Altmetric

urn-nbn
Totalt: 164 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf