%0 Journal Article %1 ls_leimeister %A Li, Mahei Manhai %A Reinhard, Philipp %A Oeste-Reiss, Sarah %A Peters, Christoph %A Leimeister, Jan Marco %D 2023 %J Information Systems (IS) %K Artificial_Intelligence Hybrid_Intelligence IT-Service-Management ITSM IT_support Value_Co-creation human-in-the-loop interactive_labeling itegpub machine_learning pub_cpe pub_jml pub_mli pub_pre pub_soe %P 102311 %R 10.1016/j.is.2023.102311 %T A Value Co-Creation Perspective on Data Labeling in Hybrid Intelligence Systems: A Design Study %U https://doi.org/10.1016/j.is.2023.102311 %X The adoption of innovative technologies confronts IT-Service-Management (ITSM) with an increasing volume and variety of requests. Artificial intelligence (AI) possesses the potential to augment customer service employees. However, the training data for AI systems are annotated by domain experts with little interest in labeling correctly due to their limited perceived value. Ultimately, insufficient labeled data leads to diminishing returns in AI performance. Following a design science research approach, we provide a novel human-in-the-loop (HIL) design for ITSM support ticket recommendations by incorporating a value co-creation perspective. The design incentivizes ITSM agents to provide labels during their everyday ticket-handling procedures. We develop a functional prototype based on 17,120 support tickets provided by a pilot partner as an instantiation and evaluate the design through accuracy metrics and user evaluations. Our evaluation revealed that recommendations after label improvement showed increased user ratings, and users are willing to contribute their domain knowledge. The improved labels can be utilized to continuously enhance the AI system as rewards showed increasing growth with decreasing marginal returns. Overall, our results emphasize agents' need for value-in-use by providing better results if they improve the labeling of support tickets pre-labeled by AI. Thus, we provide prescriptive knowledge of a novel HIL design that enables efficient and interactive labeling in the context of diverse applications of reinforcement learning systems.

@article{ls_leimeister, abstract = {The adoption of innovative technologies confronts IT-Service-Management (ITSM) with an increasing volume and variety of requests. Artificial intelligence (AI) possesses the potential to augment customer service employees. However, the training data for AI systems are annotated by domain experts with little interest in labeling correctly due to their limited perceived value. Ultimately, insufficient labeled data leads to diminishing returns in AI performance. Following a design science research approach, we provide a novel human-in-the-loop (HIL) design for ITSM support ticket recommendations by incorporating a value co-creation perspective. The design incentivizes ITSM agents to provide labels during their everyday ticket-handling procedures. We develop a functional prototype based on 17,120 support tickets provided by a pilot partner as an instantiation and evaluate the design through accuracy metrics and user evaluations. Our evaluation revealed that recommendations after label improvement showed increased user ratings, and users are willing to contribute their domain knowledge. The improved labels can be utilized to continuously enhance the AI system as rewards showed increasing growth with decreasing marginal returns. Overall, our results emphasize agents' need for value-in-use by providing better results if they improve the labeling of support tickets pre-labeled by AI. Thus, we provide prescriptive knowledge of a novel HIL design that enables efficient and interactive labeling in the context of diverse applications of reinforcement learning systems.}, added-at = {2023-11-20T07:30:55.000+0100}, author = {Li, Mahei Manhai and Reinhard, Philipp and Oeste-Reiss, Sarah and Peters, Christoph and Leimeister, Jan Marco}, biburl = {https://www.bibsonomy.org/bibtex/223a1b71438ef94a6b1b868fb5b679d14/ls_leimeister}, doi = {10.1016/j.is.2023.102311}, interhash = {744b1e2509823a3eec6851100e9da56a}, intrahash = {23a1b71438ef94a6b1b868fb5b679d14}, issn = {0306-4379}, journal = {Information Systems (IS)}, keywords = {Artificial_Intelligence Hybrid_Intelligence IT-Service-Management ITSM IT_support Value_Co-creation human-in-the-loop interactive_labeling itegpub machine_learning pub_cpe pub_jml pub_mli pub_pre pub_soe}, language = {English}, pages = 102311, timestamp = {2023-11-24T14:38:38.000+0100}, title = {A Value Co-Creation Perspective on Data Labeling in Hybrid Intelligence Systems: A Design Study}, url = {https://doi.org/10.1016/j.is.2023.102311}, year = 2023 }