Shifting ranges and changing phenology: A new approach to mining social media for species & ecosystems observations

Background/Question/Methods

Ecologists are increasingly using social media to solicit 'citizen scientists' to participate in the data collection process. Of particular interest are observations of species phenology & range to better develop a predictive understanding of how ecosystems are affected by a changing climate and human-mediated influences. Social media users are a largely untapped resource of unprompted observations of the natural world. These users' observations include information on phenological & biological phenomena such as flowers blooming, native & invasive species sightings, unusual behaviors, animal tracks, droppings, damage, feeding, nesting, etc. Our AGU2011 pilot study on the North American armadillo suggests that useful observational data can be extracted from Twitter and mapped to show the current species range for comparison to past mappings.  Here we have expanded that work by mining Twitter for a number of North American species (and ecosystem) observations to determine 1) usefulness for environmental applications such as supplementing existing databases, 2) identifying outlier phenomena, 3) guiding additional crowd-sourced studies and data collection efforts, 4) recruiting citizen scientists and 5) informing ecosystems policy-making. 

Results/Conclusions

This poster presents the results of our evaluation for a representative sample of species from a list of 200+ species for which we've collected data since August 2011. We present information on frequency of reports/sightings by day, week and month, with observations ranging from ~1/month to greater than 10 per day. We include an analysis of the challenges in distilling information from crowd-sourced observations (140-character 'tweets') and find that geolocation data is a critical issue. For example, despite the prevalence of smart phones, specific latitudinal and longitudinal coordinates are included in fewer than 10% of the observations, but this number can be substantially increased at both local & regional scales using user profile and contextual geolocation algorithms. We identify potential outlier observations and map ranges with particular attention to outliers and range fronts. Based on these results we draw conclusions on best applications for use of crowd-sourced social media observations: Identifying outliers, front-tracking and guiding traditional data collection efforts.