"OMG, from here, I can see the flames!"

Abstract

The emergence of innovative web applications, often labelled as Web 2.0, has permitted an unprecedented increase of content created by non-specialist users. In particular, Location-based Social Networks (LBSN) are designed as platforms allowing the creation, storage and retrieval of vast amounts of georeferenced and user-generated contents. LBSN can thus be seen by Geographic Information specialists as a timely and cost-effective source of spatio-temporal information for many fields of application, provided that they can set up workflows to retrieve, validate and organise such information. This paper aims to improve the understanding on how LBSN can be used as a reliable source of spatio-temporal information, by analysing the temporal, spatial and social dynamics of Twitter activity during a major forest fire event in the South of France in July 2009.

Analyzing Clusters and Constellations from Untwisting Shortened Links on Twitter Using Conceptual Graphs

“…The data is usable for a variety of purposes, perhaps most easily classified according to the technologies used. Twitter is famously used as a resource for sentiment analysis and for opinion mining [20], with a variety of purposes in mind, including product/service/company profiling, marketing purposes, political analysis and opinion polling, for example, with activist aims in mind [20], but also for stock market prediction [1], disaster alerts [7], level of interest in news articles [26] and so forth. Explicitly topic-oriented mining is of use for various purposes, such as tracking public health trends [27,21], earthquake monitoring [31], news tracking [14,23] and so on.…”

Mining photo-sharing websites to study ecological phenomena

“…Perhaps the most striking is the work of Ginsberg et al [11], who show that by monitoring the geospatial distribution of search engine queries related to flu symptoms, the spread of the H1N1 flu can be estimated several days before the official statistics produced by traditional means. DeLongueville et al [9] study tweets related to a major fire in France, but their analysis is at a very small scale (a few dozen tweets) and their focus is more on human reactions to the fire as opposed to using these tweets to estimate the fire's position and severity. In perhaps the most related existing work to ours, Singh et al [24] create geospatial heat maps (dubbed "social pixels") of various tags, including snow and greenery, but their focus is on developing a formal database-style algebra for describing queries on these systems and for creating visualizations.…”

“…Recent work has studied how to mine passively-collected data from social networking and microblogging websites to make estimates and predictions about world events, including tracking the spread of disease [11], monitoring for fires and emergencies [9], predicting product adoption rates and election outcomes [16], and estimating aggregate public mood [5,22]. In most of these studies, however, there is either little ground truth available to judge the quality of the estimates and predictions, or the available ground truth is an indirect proxy (e.g.…”

ADHD in 140 Characters or Less: an Analysis of Twitter Commentary on Attention Deficit Hyperactivity Disorder in Saudi Arabia

“…Twitter in Saudi Arabia has been analyzed for commentary on political news (Alothman [7], 2013), a women's right to drive campaign (Almahmoud [6], 2015) and women's identity (Guta and Karolak [36], 2015). Internationally, Twitter studies cover a range of topics, from the statistical properties of Twitter use (Java et al [50], 2007) and the nature of Twitter users (Krishnamurthy et al [46], 2008), to its usefulness in raising public awareness of and response to emergency events (De Longueville et al [24], 2009; Hughes and Palen [39], 2009). Research has also investigated Twitter's role in supporting individuals with mental health problems (Shepherd et al [66], 2015).…”