While crowdsourcing idea contests have the potential to harness widely distributed knowledge, the quantity of ideas and the complexity involved in idea assessment create a great effort and challenge for organizations. Drawing on tournament theory and the knowledge recombination perspective, this study proposes a model that can assist organizations in efficiently processing crowdsourced ideas by exploring two aspects: the idea content and the contest competition intensity. Analyzing a rich dataset of 16,057 ideas submitted in 61 socio-economic crowdsourcing idea contests, we find that successful ideas are more likely to stem from more distinctive knowledge while ideas that combine diverse knowledge from a broad set of topics are less likely to be successful in the idea contest. Furthermore, competition intensity weakens the positive relationship between idea distinctiveness and success, while it does not influence idea diversity. This study contributes to the growing crowdsourcing literature and offers practical guidance for crowdsourcing intermediaries and organizations.

Unlike traditional employer-employee relationships, contemporary digital platforms use algorithms to control and regulate the crowd workforce. Although prior research has expressed concerns over dehumanization stemming from algorithmic management, limited scholarly attention has been dedicated to exploring how human management can complement algorithmic approaches to address these concerns. Leveraging a case study of an on-demand food delivery platform during the COVID-19 pandemic, we developed a process theoretical model that uncovers several drivers and mechanisms essential for the transition from mechanistic algorithmic management to humanistic algorithmic management. This model elucidates the dynamic substitution and complementarity of human and algorithmic management through four key mechanisms: replacing and dampening, compensating, enabling, and synergizing. It also delineates effective humanistic management actions in scenarios in which algorithmic decisions are insufficient, which contributes to both performance and humanistic outcomes. In the realm of contemporary crowd workforce management, where digital platforms employ algorithms, this research sheds light on the unique and timely insights into the role of human managers in enhancing the strategic and humanistic values of algorithmic technology.

Traffic prediction is an important and yet highly challenging problem due to the complexity and constantly changing nature of traffic systems. To address the challenges, we propose a graph and attentive multi-path convolutional network (GAMCN) model to predict traffic conditions such as traffic speed across a given road network into the future. Our model focuses on the spatial and temporal factors that impact traffic conditions. To model the spatial factors, we propose a variant of the graph convolutional network (GCN) named LPGCN to embed road network graph vertices into a latent space, where vertices with correlated traffic conditions are close to each other. To model the temporal factors, we use a multi-path convolutional neural network (CNN) to learn the joint impact of different combinations of past traffic conditions on the future traffic conditions. Such a joint impact is further modulated by an attention generated from an embedding of the prediction time, which encodes the periodic patterns of traffic conditions. We evaluate our model on real-world road networks and traffic data. The experimental results show that our model outperforms state-of-art traffic prediction models by up to 18.9% in terms of prediction errors and 23.4% in terms of prediction efficiency.

The internationalization of Web sites requires Web designers to provide effective navigation experience for users from diverse cultural backgrounds. This research investigates the effect of cultural cognitive style on user perception of Web site structure characteristics and performance on the Web site, and the subsequent user satisfaction towards the Web site. More specifically, the authors focus on the breadth versus depth of a Web site's structure. A laboratory experiment involving participants from China and the United States was conducted to test the hypotheses. The results showed that cultural cognitive style and Web site structure indeed interact to affect user perception and performance. People with holistic and analytic cultural cognitive styles displayed different perceived navigability and user performance on “broad” and “deep” Web sites. This study adds a cultural dimension to our knowledge on how Web site structure can affect users' experience. It also suggests pragmatic strategies for Web site design practitioners to improve website design in order to produce compelling navigation experience for users from diverse cultures.