AI and the Future of Work

Permanent URI for this collectionhttps://hdl.handle.net/10125/107400

Browse

Now showing 1 - 13 of 13

Tensions in the transition of Human-AI Collaboration: A Case Study of the Nordic Renewable Energy Sector
(2024-01-03) Mohanty, Pooja; Grundstrom, Casandra; Monteiro, Eric; Zhang, Zhenyou
The increasing trends of developing and using artificial intelligence (AI) in organizations and industries are not without consequence to work practices. Theoretical suggestions for humans to collaborate with AI clash with the empirical studies, which highlight problems with implementing and using AI systems. We investigate this phenomenon through the practice lens of tensions in a Nordic renewable energy organization’s digital transformation (DT) effort. Following an ethnographic case study, we uncover four tensions felt by experts across knowledge boundaries, in group collaboration settings, disrupting normal work practices and taxing additional organizational resources. Through these tensions, we reflect on the softer and less dramatic changes and dynamics of human-AI collaboration for emerging work practices and DT in an organizational setting.
What to Learn Next? Designing Personalized Learning Paths for Re-&Upskilling in Organizations
(2024-01-03) Ritz, Eva; Freise, Leonie; Elshan, Edona; Rietsche, Roman; Bretschneider, Ulrich
The fast-paced acceleration of digitalization requires extensive re-&upskilling, impacting a significant proportion of jobs worldwide. Technology-mediated learning platforms have become instrumental in addressing these efforts, as they can analyze platform data to provide personalized learning journeys. Such personalization is expected to increase employees’ empowerment, job satisfaction, and learning outcomes. However, the challenge lies in efficiently deploying these opportunities using novel technologies, prompting questions about the design and analysis of generating personalized learning paths in organizational learning. We, therefore, analyze and classify recent research on personalized learning paths into four major concepts (learning context, data, interface, and adaptation) with ten dimensions and 34 characteristics. Six expert interviews validate the taxonomy’s use and outline three exemplary use cases, undermining its feasibility. Information Systems researchers can use our taxonomy to develop theoretical models to study the effectiveness of personalized learning paths in intra-organizational re-&upskilling.
Support Technologies in Knowledge Work: Project Team Compositions and 3D Development Pack Use in Gaming
(2024-01-03) Schulz, Anke
With the rise of artificial intelligence, private and professional users in knowledge industries can opt for unprecedented magnitudes of technology support. At the frontend, this is providing new types of users with service access. Our study looks into the implications that this has at the backend of value creation, i.e., in knowledge work. Our context is the video game industry, where projects can opt for the support of 3D development packs in making games. Transfering insights from the greater digitization literature, we consider that more experienced teams may be less prone to use them than inexperienced ones. Based on a 13-year U.S. data set covering 4,248 projects, we find that those having programmers with lower tenure, yet higher past project activity are more likely to use such technology support. Our results suggest that in contexts like gaming, support technologies may be used not only for their knowledge-complementing, but time-saving qualities.
A Framework of AI Strategy
(2024-01-03) Shi, Yao; Gebauer, Judith; Javadi, Elahe
Building a vibrant strategy for the use of Artificial Intelligence (AI) in business is becoming critical for company success in the AI era. To decode AI strategy, this study aims to address three questions: (1) what is AI strategy? (2) what are the key elements of AI strategy? (3) how can AI strategy be applied and impact a business? We define AI strategy and propose an AI strategy framework consisting of three layers: AI strategic competency, AI use cases, and AI enabling factors. Based on published cases that describe early applications of AI, we identify a bottom-up approach typically used by Small and Medium-sized Enterprises (SMEs) in building AI strategy and a top-down approach typically used by big tech firms and traditional incumbent firms. We also find differences in the core of the AI strategies that are initiated by the three types of enterprises: SMEs: survival oriented; big tech firms: AI ecosystem oriented; traditional incumbent firms: business alignment oriented.
Generative AI in Customer Support Services: A Framework for Augmenting the Routines of Frontline Service Employees
(2024-01-03) Reinhard, Philipp; Li, Mahei; Peters, Christoph; Leimeister, Jan Marco
Customer support service employees are facing increased workload, while artificial intelligence (AI) appears to possess the potential to change the way we work. With the advent of modern types of generative AI, new opportunities to augment frontline service employees have emerged. However, little is known about how to integrate generative AI in customer support service organizations and purposefully change service employee work routines. Following a multi-method qualitative research, we performed a literature review, conducted workshops, and interviewed IT support agents, managers, and AI experts. Thereby, we examine AI augmentation for frontline service employees in the context of IT support to carve out where and how GenAI can be leveraged to develop a more efficient and higher-quality customer support. Our resulting framework reveals that especially adapting solutions and retaining knowledge is subject to a high degree of AI augmentation.
Is the Human IS Researcher Dead? Long Live the AI Researcher
(2024-01-03) Müller, Sune; Kempton, Alexander; Mønsted, Troels
AI like ChatGPT sparks public concerns. These emerging technologies raise questions about what it means to be human and to what extent they will support or replace existing jobs. As scholars, we are also forced to reckon with what it means to be a researcher and how AI influences our identity and profession. We address the latter questions based on an extensive interview with ChatGPT and its self-assessment of research capabilities based on the Researcher Development Framework. The assessment shows expert-level capabilities within some areas, but is open to divergent interpretations. We suggest the AI user, the AI prompter, and the AI sidekick as potential future roles that we may assume. We discuss whether the human researcher is dead and the implications of AI for our researcher identity. We suggest research questions that will help us prepare for the future, maintain agency, redefine our identity, and influence future AI development.
Persistence, Emergence, and Fadeout: Influence of AI Teammates on the Salience of Human Identities at Work
(2024-01-03) Liang, Qingyu; Banks, Jaime; Gou, Juanqiong
Increasingly communicative and autonomous artificial intelligence (AI) technologies are becoming essential partners in workspaces and changing how people work. However, it is not yet well understood how introducing AI teammates into working contexts may impact how people see themselves—especially as AI imitates human intelligence to perform tasks usually done by humans. To address this gap, this experimental study examined how the ontological category of office-work teammates (human or AI) may influence the salience of people’s identities. Participants were assigned to work with a teammate (human or AI) in an office-process simulation; they named salient general and work-related identities before and after completing the simulation. Findings indicate AI teammates alter the salience of some human identities, as some new identities emerge and others fade as irrelevant—however, some identities persist or are reframed as people make sense of the work arrangement.
Fairness in Algorithmic Management: Bringing Platform-Workers into the Fold
(2024-01-03) Jabagi, Nura; Croteau, Anne-Marie; Audebrand, Luc; Marsan, Josianne
On digital labor platforms, algorithms execute a range of decisions including work assignments, performance evaluation, etc. Although algorithmic decision-making is a key feature of platform work, our understanding of how people perceive decisions made by algorithms – particularly in terms of the fairness of their processes and outcomes – remains underdeveloped. The impacts of such perceptions on job satisfaction and perceived organizational support (POS) are also still under exploration with some scholars challenging the possibility of POS among transient platform workers. In this paper, we explored the impacts of the perceived procedural and distributive fairness of algorithms operating in a paradigmatic context of algorithmic management, namely Uber. Drawing on the Theory of Organizational Justice, and a survey of 435 Uber drivers, we not only find that independent platform workers can experience POS, but that the fairness of managerial algorithms (in particular their outcomes) can play a critical role in stimulating such perceptions.
Considerations on Human-AI Collaboration in Knowledge Work – Recruitment Experts’ Needs and Expectations
(2024-01-03) Ala-Luopa, Saara; Koivunen, Sami; Olsson, Thomas; Väänänen, Kaisa
Organizations' decision-making processes are increasingly supported by novel AI applications. While intelligent systems appear promising for enhancing various professional tasks, domain experts’ perceptions of the adoption and use of AI remain understudied. Following a human-centered design approach, this qualitative interview study (N=15) explores the potential of AI applications from recruitment experts’ perspectives. The results of the study emphasize the collaborative nature of AI: recruitment experts anticipate AI to augment their expertise positioning as a complementary information source. Domain experts would then evaluate and justify this outcome according to certain recruitment situations and combined with recruitment experts’ tacit knowledge. Novel AI applications are expected to align with underlying social and societal factors that guide the domain experts’ work practices. The results provide qualitative understanding into domain experts’ user experience and human-AI collaboration in knowledge work, offering insight into human-centered AI design and development.
Predicting Job Automation: What have we observed?
(2024-01-03) Sampson, Scott
This research considers the ability to predict job automation based on two models. The first is a job model developed by Frey and Osborn and published in 2017. With 12000+ citations, that article appears to be the most highly cited academic article on predicting job automation. The second is a job automation model developed by Sampson and published in 2021. Coincidentally, both models were developed using the same U.S. Department of Labor database called O*Net, although using different data from different years. We use historical and current O*Net data to see how each model does in predicting observed changes in job automation over a wide range of jobs. A surprising finding is a negative correlation between degrees of automation for various jobs and changes in the degree of automation over the subsequent decade. This analysis leads to interesting theories about how job automation can be predicted, including an AI explanation.
The Effect of IS Engagement on Generative AI Adoption
(2024-01-03) De Vreede, Triparna; Singh, Vivek Kumar; De Vreede, Gert-Jan; Spector, Paul
Artificial Intelligence (AI) technology is developing at an unprecedented rate. For organizations to reap the benefits of AI, their workforce need to embrace them and adopt them into their work practices. Using Social Cognitive Theory as a theoretical lens, we examine how users’ engagement with AI technologies influences their intention to use them. To this end, we adopt a multi-dimensional perspective on IS engagement and also explore how AI familiarity relates to users’ engagement. We find support for the positive association between AI familiarity and IS engagement as well as between IS engagement and Intention to use. Implications are discussed.
Tool, Teammate, Superintelligence: Identification of ChatGPT-Enabled Collaboration Patterns and their Benefits and Risks in Mutual Learning
(2024-01-03) Cheng, Xusen; Zhang, Shuang
The emergence of ChatGPT has brought new opportunities for AI-enabled collaboration. Due to the amazing performance of ChatGPT, the collaboration between AI and humans is no longer limited to a single pattern. However, previous studies focused on AI working together as a teammate, with little analysis of different collaboration patterns and their impacts. We conducted interviews, encoded data building on grounded theory, developed a ChatGPT-enabled collaboration process, and identified three collaboration patterns: ChatGPT serves as a tool, teammate, and superintelligence for collaboration. Additionally, this study also ascertained the benefits (i.e., improve search efficiency, improve team motivation, enrich and refine ideas, and improve thinking ability) and risks (i.e., increase search time, reduce willingness for face-to-face communication, make the collaborative atmosphere negative, ChatGPT addiction, and cognitive rigidity) in mutual learning between ChatGPT and humans. Finally, theoretical and practical implications are provided.
Introduction to the Minitrack on AI and the Future of Work
(2024-01-03) De Vreede, Triparna; Cheng, Xusen; Siemon, Dominik

Browse

Recent Submissions