Search

Marshall McLuhan once proposed the concept of “global village,” believing that with the help of electronic media, Earth has become indistinguishable from a community, and there is only one Earth for human beings and one world for all countries. Today, with the continuous development of media technology, the concept of a human destiny community has also gained the general consensus of people around the world. The global value of the human destiny community encompasses the interdependent concept of international power, the concept of common interests, the concept of sustainable development, and the concept of global governance. In particular, the concepts of sustainable development and global governance have been advocated by the public, which in turn has led to extensive public discussions on Socioscientific Issues (SSI), in which the teaching of SSI is gradually considered by the international science education community as one of the important goals of science education. The current issues and challenges facing SSI teaching and how immersive media technologies can facilitate SSI teaching have become important issues of keen public interest.

University of Technology Sydney. Faculty of Engineering and Information Technology. Causality is a fundamental component in all fields of science. In contrast to associational dependencies that are widely used in existing predictive machine learning and data-mining methods, causality implies the mechanism of how variables take their values and how the change of causes would lead to the change in the outcome. In the era of big data, for scientific discovery and rational decision-making, we fundamentally need methods for learning causal relationships between variables and estimating causal effects from observational data. In this thesis, we aim to develop new models and algorithms for learning causal relationships and estimating causal effects using observational data. In particular, for the purpose of modelling and learning causal relationships from observational data, we study dynamic causal systems with feedbacks. To overcome the weakness of existing models that are unable to model both instantaneous and cross-temporal causal relations simultaneously, we propose a First-order Causal Process (FoCP) model and a causal structure learning algorithm to learn the causal graph of FoCPs from time series. For the purpose of estimating treatment effects, we investigate a range of existing methods for causal effect estimation, and propose three new methods using advanced machine learning techniques. First, to relieve the high-variance issue of the classic Inverse Propensity Weighting (IPW) estimator and thus to get more stable treatment effect estimates, we reframe it to the importance sampling framework and propose a novel Pareto-smoothing method using the generalized Pareto distribution from the extreme value statistics. Second, for causal inference with unobserved confounders, we take advantage of proxy variables and use deep latent variable models to model the underlying data-generating process. Building on recent advances in Bayesian inference and deep generative models, we propose a Causal Effect Implicit Generative Model (CEIGM). Finally, with an observation that most of existing methods for causal inference are essentially indirect in that they estimate the target treatment effects by first estimating other auxiliary quantities, we propose the idea of direct treatment effect estimation. Based on this idea, we further propose two deep neural networks for direct treatment effect estimation. We evaluate all the methods proposed in this thesis using simulated, semi-simulated or real-world data. Experiment results show that they perform generally better than their competitors. Given the key importance of learning causality and causal inference in both theory and real-world applications, we argue that our proposed models and algorithms are of both theoretical and practical significance.