“Social sensing” is a form of crowd-sourcing that involves systematic analysis of digital communications to detect real-world events. Here we consider the use of social sensing for observing natural hazards. In particular, we present a case study that uses data from a popular social media platform (Twitter) to detect and locate flood events in the UK. In order to improve data quality we apply a number of filters (timezone, simple text filters and a naive Bayes ‘relevance’ filter) to the data. We then use place names in the user profile and message text to infer the location of the tweets. These two steps remove most of the irrelevant tweets and yield orders of magnitude more located tweets than we have by relying on geo-tagged data. We demonstrate that high resolution social sensing of floods is feasible and we can produce high-quality historical and real-time maps of floods using Twitter.

Artificial Intelligence in Education (AIED) has witnessed significant growth over the last twenty-five years, providing a wide range of technologies to support academic, institutional, and administrative services. More recently, AIED applications have been developed to prepare students for the workforce, providing career guidance services for higher education. However, this remains challenging, especially concerning the rapidly changing labour market in the IT sector. In this paper, we introduce an AI-based solution named C3-IoC (https://c3-ioc.co.uk), which intends to help students explore career paths in IT according to their level of education, skills and prior experience. The C3-IoC presents a novel similarity metric method for relating existing job roles to a range of technical and non-technical skills. This also allows the visualisation of a job role network, placing the student within communities of job roles. Using a unique knowledge base, user skill profiling, job role matching, and visualisation modules, the C3-IoC supports students in self-evaluating their skills and understanding how they relate to emerging IT jobs.

Heatwaves cause thousands of deaths every year, yet the social impacts of heat are poorly measured. Temperature alone is not sufficient to measure impacts and “heatwaves” are defined differently in different cities/countries. This study used data from the microblogging platform Twitter to detect different scales of response and varying attitudes to heatwaves within the United Kingdom (UK), the United States of America (US) and Australia. At the country scale, the volume of heat-related Twitter activity increased exponentially as temperature increased. The initial social reaction differed between countries, with a larger response to heatwaves elicited from the UK than from Australia, despite the comparatively milder conditions in the UK. Language analysis reveals that the UK user population typically responds with concern for individual wellbeing and discomfort, whereas Australian and US users typically focus on the environmental consequences. At the city scale, differing responses are seen in London, Sydney and New York on governmentally defined heatwave days; sentiment changes predictably in London and New York over a 24-h period, while sentiment is more constant in Sydney. This study shows that social media data can provide robust observations of public response to heat, suggesting that social sensing of heatwaves might be useful for preparedness and mitigation.

Twitter has become an important platform for geo-spatial analyses, providing high-volume spatial data on a wide variety of social processes. Understanding the relationship between population density and Twitter activity is therefore of key importance. This study reports a systematic relationship between population density and Twitter use. Number of tweets, number of users and population per unit area are related by power law functions with exponents greater than one. These relations are consistent with each other and hold across a range of spatial scales. This implies that population density can accurately predict Twitter activity, but importantly, it also implies that correct predictions are not given by a naive linear scaling analysis. The observed super-linearity has implications for any spatial analyses performed with Twitter data and is important for understanding the relationship between Twitter use and demographics. For example, the robustness of this relationship means that we can identify ‘anomalous’ geographic areas that deviate from the observed trend, identifying several towns with high/low usage relative to expectation; using the scaling relationship we are able to show that these anomalies are not caused by age structure, as has been previously proposed. Proper consideration of this scaling relationship will improve robustness in future geo-spatial studies using Twitter.