Welcome to the 3rd International Workshop on the Social Web for Environmental and Ecological Monitoring (SWEEM 2018)

The exponential growth of the popularity of social media has provided not only novel techniques for public communication and engagement, but has also generated unprecedented volumes of publicly-available, user-generated social media content. These trends open new opportunities for ecological and environmental applications, both in terms of alternative data sources and novel approaches for interacting with the public.

The goal of the workshop is to bring together a combination of academic and industrial participants to discuss ideas, challenges, and solutions at the intersection of Social Media and Environmental/Ecological Science.

Check out the call for papers!

 
Keynotes

Gretchen Lebuhn (San Francisco State University)
https://faculty.sfsu.edu/~lebuhn/
The Great Sunflower Project

Identifying the spatial patterns of pollinator visitation rates is key to identifying the drivers of differences in pollination service and the areas where pollinator conservation will provide the highest return on investment. However, gathering pollinator abundance data at the appropriate regional and national scales is untenable. As a surrogate, habitat models have been developed to identify areas of pollinator losses but these models have been developed using expert opinion based on foraging and nesting requirements. Thousands of citizen scientists across the United States participating in The Great Sunflower Project (www.GreatSunflower.org) contribute timed counts of pollinator visits to a focal sunflower variety planted in local gardens and green spaces.

 

Gerald Friedland (Lawrence Livermore National Labs and University of California, Berkeley)
https://www1.icsi.berkeley.edu/~fractor/
Field Studies with Multimedia Big Data: Opportunities and Challenges

Social media users are continuously and increasingly sharing all kinds of data about the world. They do this for their own reasons, of course, not to provide data for field studies—but the trend does present a great opportunity for scientists. The Yahoo Flickr Creative Commons 100 Million (YFCC100M) dataset comprises 99 million images and nearly 800 thousand videos from Flickr, all shared under Creative Commons licenses. To enable scientists to leverage these media records for field studies, we present a new framework that extracts targeted subcorpora from the YFCC100M, in a format usable by researchers who are not experts in big data retrieval and processing. This talk discusses a number of examples from the literature—as well as some entirely new ideas—of natural and social science field studies that could be piloted, supplemented, replicated, or conducted using YFCC100M data.

 

Shawn Newsam (University of California, Merced)
https://www.ucmerced.edu/content/shawn-newsam
Computer Science Meets the Environment: Three Projects

I will provide an overview of three projects. First, on using webcameras to estimate atmospheric visibility with the ultimate goal of monitoring particulate pollution. Second, on proximate sensing, a framework for performing novel geographic discovery from ground-level images and videos. And, third, on the automatic detection of bird calls in citizen-sourced audio recordings for mapping biodiversity.

 

 

Yu-Ru Lin (University of Pittsburgh)
http://www.yurulin.com/
Event Analytics for Strengthening Community Resilience in a Cyber-Physical Society

There has been an increasing number of large-scale crises, including natural disasters or armed attacks, that have posed enormous and ongoing threats to communities and society at large. During mass emergencies, victims, responders, and volunteers increasingly use social media and mobile devices to provide timely situational information, from reporting damages, requesting and coordinating help, to expressing social needs and support. There is a growing need for developing new understanding and techniques that help analyze the vast volumes of social data. In this talk, I will discuss how social data and machine learning techniques together allow better preparation for emergency events and offer insights into the immediate and longer-term impact of disasters. These results offer practical implications for how to strengthen community resilience in a cyber-physical society.


Partners:

CHEST EU Project