Learning Machine Learning Open Workgroup (LMLow) Hackathon

Following on from the successes of the first three sessions of LMLOW, we are proud to announce our first ever hackathon event! The event will be entirely hands-on and provide an opportunity for individuals to gain practical experience in utilising the two methodologies that we have covered so far: (1) Regression Trees and Gradient Boosting, and (2) Word2vec and text mining

The hackathon will focus on analysing a single data set: AirBnb reviews in London provided by Inside Airbnb. The data include geographically referenced reviews for airbnb lodgings and includes a mixture of numerical and text data. The data can be found here (search for London). 

Please come prepared having examined the data source and the potential questions that could be explored using the data. During the event, individuals will be split into small teams who will identify and explore research questions utilising the two methodologies, under the guidance of our team of experts. Participants will be required to bring their own laptop with relevant statistical software pre-installed (e.g. R/RStudio, Python, QGIS etc). There will be a prize for the team who completes the best project.
You can sign up for the event at this link.

Latest QWeCI Project Newsletter now available

Post by Andrew McCaldon

I am the project secretary and Dr. Andy Morse is the coordinator of the QWeCI Project – Quantifying Weather and Climate Impacts on Health in Developing Countries.

In this project, researchers across 13 European and African research institutions work together to integrate data from climate modelling and disease forecasting systems to predict the likelihood of an epidemic up to six months in advance.  The research, funded by the European Commission Seventh Framework programme, focuses on climate and disease in Senegal, Ghana and Malawi and aims to give decision–makers the necessary time to deploy intervention methods to help prevent large scale spread of diseases such as Rift Valley Fever and malaria.

Read about the recent activity in the latest QweCI Project newsletter, which can be downloaded here, and more information can be found here.

A newbie to the School

Post by Dr Chris Lloyd

As a new arrival in the School, I have been trying to adjust to how things work in the University. I spent my last academic year at Queen’s University Belfast on sabbatical (a year off teaching and admin responsibilities to pursue research). During this time I have been working on three book projects (not to be recommended at one go!) – an introductory text on Geographical Information Systems, a research-level book on exploring spatial scale in geography, and an edited book on segregation. Spatial scale is at the heart of my research interests; the relationships between population variables (for example, employment status and housing tenure) change as the spatial scale of measurement is adapted – the relationship will be different if we use small Census areas or large Census areas. Scale also links directly to my interest in segregation – a group may appear segregated (separated from members of other groups) if we use small Census areas, and mixed if we use large Census areas. So, we must understand scale effects if we are to characterise segregation, in the same way that we need to know something about the scale of variation in deprivation if we are to characterise deprivation.

Modelling travel time: the local time cost of travelling 100m in Belfast Urban Area.

Another interest of mine is in how we can model interactions between people using quantitative data. The places that we visit on a day-to-day basis are selected for a variety of reasons – because we work there, we have friends or family who live there, there are shops or other facilities, or we just travel through the area to get to somewhere else. Most spatial statistical methods use very simple definitions of neighbourhoods, and they are usually based on the assumption that the likelihood of travel decreases in proportion to distance from the place of residence. Part of my research explores ways to more realistically model the potential movement of people and the degree to which they interact with others – a link back to the theme of segregation.

In my short time in the School of Environmental Sciences, it has already proved to be a collegial and stimulating place to work, and I am very pleased to be moving into such a great working environment!