Study of microblog activity on Cyanobacterial Harmful Algal Blooms

AbstractIn recent years, social media has revolutionizedcitizen science activities. Given its popularity among peopleand communities, these social media services could be usedeffectively for environmental surveillance. However in socialmedia, people use different terms to refer to same event forexample, Blue Green Algae, Cyanobacteria, Algae Bloom andRed Tide refer to same event but one is very technical and otheris more generic term. The technical terms are normally knownto field experts or the domain scientists which inherently wouldmean more reliable information on social media but the moregeneric term is used by people of various backgrounds puttinga question on the trustworthiness of the post. Moreover, theuser base and the number of posts for more technical terms arerelatively less compared to the generic terms. But the dichotomyis that the more common the term, the more noisy the data. Onecan say using generic terms to track the environmental eventswould be more effective. But the social media data has lot offlux thus using train once and classify ever model of machinelearning will miss to classify many of the relevant events asshown in the paper. Our research seeks to explore the variousopportunities, challenges and approaches in using social mediafor environmental monitoring.Keywords- (citizen science; environmental surveillance;)