IT Enabled Collaboration for Development
Permanent URI for this collection
Browse
Recent Submissions
Item Navigating Task Delegation in Human-Automation Teams: The Role of Task Difficulty and Cognitive Aids(2025-01-07) Li, Zhuo; Gao, Hongyu; Cui, Xiaocong; Wang, Pengcheng; Zhang, DongliFor decades, researchers in Human-Automation Interaction (HAI) have been striving to address the issues of automation underutilization and overreliance. However, few studies have considered the impact of task characteristics, such as task difficulty, on how humans delegate tasks to automation. This study draws insights from the Better-Than-Average (BTA) and Worse-Than-Average (WTA) effects to propose that task difficulty significantly influences automation use. We further explore the use of cognitive aids as a strategy to reduce humans' perception of task difficulty and mitigate automation overreliance. The theoretical and practical implications of our findings are discussed.Item Investigating the Impact of Disclosing Generative AI’s Involvement in Video Advertising(2025-01-07) Wang, Tianzi; Cheng, Xusen; Lei, Siyu; Li, Yixuan; Zhang, Xiaoling; Wang, PinshuThe deployment of generative artificial intelligence (GAI) in advertising industry has witnessed a significant increase during recent years. However, consensus on whether consumers should be informed of generative AI’s involvement in video advertisement creation and how to mitigate the potential negative effects caused by such disclosure has not been well investigated. Drawing upon signaling theory, this research aims to investigate the effect caused by generative AI involvement disclosure in video advertisement. Besides, we provide possible explanation by examining the mediating role of authenticity perception. In addition, we suggest that the potential negative effects caused by AI involvement disclosure could be alleviated by adjusting the timing of disclosure. In this paper, we will discuss three experimental studies with the aim of testing the direct effects, the possible explanation, and the effects of timing strategy. This research will contribute to both theory development and the practice of AI deployment and human-AI collaboration within advertising field.Item Designing Incentive Mechanisms for Sustainable and High-Quality Data Sharing in Federated Learning(2025-01-07) Ai, Qiuyuan; Wang, Cong; Song, JieFederated learning is a promising privacy-preserving approach for data collaboration, where the continued participation of data owners is crucial for sustainability. In this paper, we propose incentive mechanisms for FL to ensure stable and high-quality data collaboration. We model the long-term data sharing problem in FL as a repeated game and design the incentive mechanisms based on fine-grained payoff construction and data characteristics. The designed incentive mechanisms provide a reasonable profit allocation to participants. We derive the boundary conditions of long-term cooperation with two Bayesian strategies, addressing the inflexibility and limitations of classic strategies. Our findings show that stable cooperation depends on various factors, including task difficulty, participants' data quality, cost sensitivity, and discount rate. Among the incentive mechanisms we provide, the marginal-improvement-based scheme proves to be the most sensitive to data quality, tending to promote cooperation among clients with high data quality. Extensive numerical simulations and case studies on data sharing are conducted to validate the theoretical analysis. Our research provides insights into stable and high-quality data sharing in various applications.Item Disentangling the Factors Driving Friendship Formation: An LLM-Enhanced Graph Convolutional Approach for Friend Recommendation(2025-01-07) Li, Dongyang; Wu, Yuhan; Sun, Jianshan; Jiang, YuanchunThe global proliferation of social media has provided a unique platform for cross-cultural exchange, greatly enhancing interactions between users from different cultural backgrounds through friend recommendation systems. However, the highly complex and intrinsically coupled nature of factors driving friendship formation makes it difficult for traditional methods to effectively predict and recommend genuinely deep social connections. Therefore, this study proposes leveraging emerging information technologies, specifically deep learning, to optimize and improve friend recommendation systems on social media platforms. This paper introduces a novel personality trait disentanglement method. By using large language models to extract personality factors from user text, we constructed a multi-subgraph convolutional method driven by personality traits. This enables the model to clearly distinguish the mechanisms of different personality factors. Additionally, we designed a shared attention layer to adaptively learn the importance weights of different personality traits, and implicit representations to capture non-personality-driven factors. Our research combines deep learning with personality trait analysis to foster deeper interpersonal understanding and cultural exchange, thereby enhancing the quality and breadth of interactions on social networks globally.Item Unveiling the Presentation Threshold Effect: The Impact of Product Rotation on Real-time Sales in Live Streaming Commerce(2025-01-07) Yu, Haolong; Wang, Hongpeng; Fan, Weiguo (Patrick)This research investigates a largely unexamined feature within the realm of live streaming, product rotation. Leveraging the minute-level product sales data from TikTok, we delve into the impact of product rotation on real-time sales. Our study unveils a novel phenomenon dubbed the “presentation threshold effect,” wherein a significant increase in sales preceding the end of the product presentation, followed by a distinct drop at the moment of product rotation. Further analyses of the underlying mechanism causally reveal that the threshold effect occurs primarily among live streams with high viewer stickiness. Additionally, we find that factors such as inter-product similarity, repetition of products, and timing of presentation significantly impact the magnitude of the presentation threshold effect. These findings contribute to the literature on live streaming strategies while offering streamers valuable insights into consumer purchasing behavior. By examining factors related to product sequencing, streamers can craft more strategic product lineups, including decisions on the placement of similar or identical products and the optimal timing for implementing lucky draws.Item Introduction to the Minitrack on IT Enabled Collaboration for Development(2025-01-07) Yan, Xiangbin; Bajwa, Deepinder; Cheng, Xusen