Colonial girls' literature and the politics of archives in the digital age

In this paper we examine the politics of print and digital archives and their implications for research in the field of historical children's literature. We use the specific example of our comparative, collaborative project 'From Colonial to Modern: Transnational Girlhood in Australian, New Zealand and Canadian Print Cultures, 1840-1940' to contrast the strengths and limitations of print and digital archives of young people's texts from these three nations. In particular, we consider how the failure of some print archives to collect ephemeral or non-canonical colonial texts may be reproduced in current digitising projects. Similarly, we examine how gaps in the newly forged digital "canon" are especially large for colonial children's texts because of the commercial imperatives of many large-scale digitisation projects. While we acknowledge the revolutionary applications of digital repositories for research on historical children's literature, we also argue that these projects may unintentionally marginalise or erase certain kinds of children's texts from scholarly view in the future.

Differentially private random forest with high utility

Privacy-preserving data mining has become an active focus of the research community in the domains where data are sensitive and personal in nature. For example, highly sensitive digital repositories of medical or financial records offer enormous values for risk prediction and decision making. However, prediction models derived from such repositories should maintain strict privacy of individuals. We propose a novel random forest algorithm under the framework of differential privacy. Unlike previous works that strictly follow differential privacy and keep the complete data distribution approximately invariant to change in one data instance, we only keep the necessary statistics (e.g. variance of the estimate) invariant. This relaxation results in significantly higher utility. To realize our approach, we propose a novel differentially private decision tree induction algorithm and use them to create an ensemble of decision trees. We also propose feasible adversary models to infer about the attribute and class label of unknown data in presence of the knowledge of all other data. Under these adversary models, we derive bounds on the maximum number of trees that are allowed in the ensemble while maintaining privacy. We focus on binary classification problem and demonstrate our approach on four real-world datasets. Compared to the existing privacy preserving approaches we achieve significantly higher utility.