Recent & Upcoming Talks

Using Machine Learning and Twitter Data to Profile Attitudes Towards Immigration

Immigration is a key ingredient for social cohesion and economic development. Yet, it is often portrayed as a major threat to national identity, values, economic stability and security, resulting in acts of intolerance, discrimination, racism, xenophobia and violent extremism. Understanding how misperceptions towards immigration are formed and shaped is key to address combat mis-representations of immigrants. Typically attitudes towards immigration are studied based on qualitative and nationally representative surveys but they offer low population coverage, coarse geographical resolution and slow data collection. Social media offers dynamic and open space to better understand experiences and public opinion about immigration. While some bias exists, social media data are produced at unprecedented temporal frequency, geographical granularity and is accessible in real time. This paper aims to measure and better understand attitudes towards immigration in Chile using Twitter data. Key findings indicate that negative attitudes emerge from a reduced number of users, and are more commonly manifested and intensify during negative immigrant news reflecting arguments of job competition and stricter immigration regulation. Positive attitudes are expressed by a more diffused number of users and are predominantly express to manifest support during specific events reflecting supportive arguments for immigrants’ human and civil rights.

Using Machine Learning and Twitter Data to Profile Attitudes Towards Immigration

Immigration is a key ingredient for social cohesion and economic development. Yet, it is often portrayed as a major threat to national identity, values, economic stability and security, resulting in acts of intolerance, discrimination, racism, xenophobia and violent extremism. Understanding how misperceptions towards immigration are formed and shaped is key to address combat mis-representations of immigrants. Typically attitudes towards immigration are studied based on qualitative and nationally representative surveys but they offer low population coverage, coarse geographical resolution and slow data collection. Social media offers dynamic and open space to better understand experiences and public opinion about immigration. While some bias exists, social media data are produced at unprecedented temporal frequency, geographical granularity and is accessible in real time. This paper aims to measure and better understand attitudes towards immigration in Chile using Twitter data. Key findings indicate that negative attitudes emerge from a reduced number of users, and are more commonly manifested and intensify during negative immigrant news reflecting arguments of job competition and stricter immigration regulation. Positive attitudes are expressed by a more diffused number of users and are predominantly express to manifest support during specific events reflecting supportive arguments for immigrants’ human and civil rights.

Using Twitter and Machine Learning to Understand Attitudes Towards Immigration

Immigration is a key ingredient for social cohesion and economic development. Yet, it is often portrayed as a major threat to national identity, values, economic stability and security, resulting in acts of intolerance, discrimination, racism, xenophobia and violent extremism. Understanding how misperceptions towards immigration are formed and shaped is key to address combat mis-representations of immigrants. Typically attitudes towards immigration are studied based on qualitative and nationally representative surveys but they offer low population coverage, coarse geographical resolution and slow data collection. Social media offers dynamic and open space to better understand experiences and public opinion about immigration. While some bias exists, social media data are produced at unprecedented temporal frequency, geographical granularity and is accessible in real time. This paper aims to measure and better understand attitudes towards immigration in Chile using Twitter data. Key findings indicate that negative attitudes emerge from a reduced number of users, and are more commonly manifested and intensify during negative immigrant news reflecting arguments of job competition and stricter immigration regulation. Positive attitudes are expressed by a more diffused number of users and are predominantly express to manifest support during specific events reflecting supportive arguments for immigrants’ human and civil rights.

Measuring Urban Forest Using Street-Level Imagery and Deep Learning

We develop a method based on computer vision and a hierarchical multilevel model to derive an Urban Street Tree Vegetation Index which aims to quantify the amount of vegetation visible from the point of view of a pedestrian. Our approach unfolds in two steps. First, areas of vegetation are detected within street-level imagery using a state-of-the-art deep neural network model. Second, information is combined from several images to derive an aggregated indicator at the area level using a hierarchical multilevel model. The comparative performance of our proposed approach is demonstrated against a widely used image segmentation technique based on a pre-labelled dataset. The approach is deployed to a real-world scenario for the city of Cardiff, Wales, using Google Street View imagery. Based on more than 200,000 street-level images, an urban tree street-level indicator is derived to measure the spatial distribution of tree cover, accounting for the presence of obstructing objects present in images at the Lower Layer Super Output Area (LSOA) level, corresponding to the most commonly used administrative areas for policy-making in the United Kingdom. The results show a high degree of correspondence between our tree street-level score and aerial tree cover estimates. They also evidence more accurate estimates at a pedestrian perspective from our tree score by more appropriately capturing tree cover in areas with large burial, woodland, formal open and informal open spaces where shallow trees are abundant, in high density residential areas with backyard trees, and along street networks with high density of high trees. The proposed approach is scalable and automatable. It can be applied to cities across the world and provides robust estimates of urban trees to advance our understanding of the link between mental health, well-being, green space and air pollution.

How Do Local Labor Markets Looks From Above? An Automated Satellite Imagery Approach

Administrative areas do not accurately reflect the contemporary spatial manifestation of labour market linkages. Local labour market areas (LLMAs) have been shown to provide a better representation of geographic labour market activity. Traditionally LLMAs are delineated based on commuting flow data. However, commuting data are expensive to collect, are sporadically collected in developed countries and rarely available in less developed countries. Yet, recent advances in computing capacity and increased availability of satellite imagery offers a unique opportunity to generate LLMAs in poor environment context in a cheap, frequent and automated way. This papers aims to develop an automated satellite-based approach to define LLMAs.

Migration, Cities & Big Data

This presentation summarises collaborative work on internal migration in Latin American cities. It also proposes ways how twitter data and machine learning can be used to measure internal migration and an approach to measure the relative importance …