How social networks are evolving into useful scientific tools

Have you ever wondered what happened to the holiday pictures you uploaded to Facebook or Flickr last year? Seen by a few envious friends and forgotten about?

Hundreds of thousands of images are being posted to social websites, showing a unique glimpse of the underwater world. Analysis of a small subset of these images show very high accuracy of image tagging (93% were annotated correctly) which makes them useful as a primary data source for conservation research. By analysing the text associated with the uploaded images it is possible to map where different species live around the world, what they eat, what eats them and whether changes are occurring to their populations.

This prototype allows you to explore the messages and images posted on Facebook by combining the data with a marine species taxonomy.

This is a non-commercial research project from the Coral Reef Research Unit and the University of Essex aiming to improve our understanding of marine life.

Search or explore for a species you are interested in, or find out more about how this works.

Crowdsourcing on Social Networks

Social networks can be seen as decentralised and self-organised crowdsourcing systems that are becoming increasingly popular (see chart, right, showing the rate of data being added per month to Facebook groups).

Tasks are created by the users, so they are motivated to participate, and the natural language of the interface allows them to express their emotions whilst solving the tasks.

We call this approach groupsourcing, completing a task using a group of intrinsically motivated people of varying expertise connected through a social network.

Challenges:

* unstructured data
* not publically archived
* difficult to automatically analyse
* access not simple
* uneven distribution of workload

Social Learning

Users on social networks teach each other in an ad-hoc manner and engage in learning that suits their interests and time restraints. Some users will learn enough to become pseudo-experts and reduce the bottleneck of a few experts having to do the majority of the work.

Knowledge Discovery

The opportunity to discover something unknown is a driving user motivation behind citizen science. Expert users can access important or novel message threads about associated entities, temporal shifts, geographic distribution and other niche dimensions that could be indicators, in this case, of ecosystem changes caused by pollution, overfishing or climate change.

Read more about data quality in the full conference paper or read the shorter paper describing the applications of this prototype.

How it all began...

One of the most frequent questions I'm asked is how does a computer scientist end up working working in marine biology? The simple answer is that since 2004 I've been SCUBA diving and taking underwater photographs, with a keen interest in Opistobranchia (sea slugs). Like many other divers I would photograph things I didn't know how to identify and would scour books and websites hoping to find a match.

In 2013 I worked with Operation Wallacea running the nudibranch (sea slug) science projects on a small island in the Wakatobi marine reserve in Indonesia. With limited access to the Internet we had just enough bandwidth to upload small images to Facebook groups for identification (such as the image of Thuridilla hoffae, right). We would receive answers from people around the world within minutes, confirming the species that we had seen.

So I focused my research skills on this phenomenon, to find out how accurate the identifications were, and built this website to allow easier access to this incredible collaboratively-built resource.

Jon Chamberlain (Researcher at the University of Essex and Coral Reef Research Unit)