Abstract

Speaker: Krittika D’Sliva

Title: Modeling Urban Environments with Complex Networks

Abstract Urban environments have become a popular application in network science because of their complex dimensionality, from individuals moving from venue to venue to neighborhood connectivity changing over time. Better understanding cities is valuable as it enables us to model and predict changes in issues such as congestion, energy consumption, and environmental destruction. My work focuses on harnessing traditional machine learning algorithms and network metrics to reveal properties of cities around the world. I will describe two recent works. In the first, we utilize trends from temporally similar areas in a city as features to predict the demand of a new venue. In the second, we demonstrate how a number of network and transport features can enable us to predict whether a business will survive or fail.

————————

Speaker: Xiao Zhou

Title:Discovering Latent Patterns of Urban Cultural Interactions in WeChat for Modern City Planning

Abstract The optimal allocation of cultural establishments and related resources across urban regions becomes of vital importance, as it can reduce financial costs in terms of planning and improve quality of life in the city, more generally. We make use of a large longitudinal dataset of user location check-ins from the online social network WeChat to develop a data-driven framework for cultural planning in the city. We exploit rich spatio-temporal representations on user activity at cultural venues and use a novel extended version of the traditional latent Dirichlet allocation model that incorporates temporal information to identify latent patterns of urban cultural interactions. Using the characteristic typologies of mobile user cultural activities emitted by the model, we determine the levels of demand for different types of cultural resources across urban areas. We then compare those with the corresponding levels of supply as driven by the presence and spatial reach of cultural venues in local areas to obtain high resolution maps that indicate urban regions with lack of cultural resources, and thus give suggestions for further urban cultural planning and investment optimisation.

————————

Speaker:Sian Gooding

Title: Contextual Text Simplification

Abstract Textual simplification can be defined as any process that reduces the syntactical or lexical complexity of a text, while attempting to preserve its meaning and information content. In this talk I will explain the pros and cons of current state of the art deep learning simplification techniques. Additionally, I shall present joint work with Dr. Ekaterina Kochmar on contextual lexical simplification.

————————