IUCN / SSC Cat Specialist Group - Digital Cat Library |
|
||||||||||
|
||||||||||
|
|
| Ribeiro, Y.G.G. | |
| Social media in the context of land mammals conservation: connecting human dimension with the digital universe | |
| 2020 Full Book | |
The volume of data from social media and their uses have grown in number and complexity and have been used in the most diverse areas, from marketing to opinion monitoring. Strategies for obtaining, treating and analyzing them are necessary, since they vary enormously in relation to its characteristics (dimensions) of data. These data have a strong potential to contribute, for example, to the monitoring of public opinion in relation to conservation-related events. Despite the growing popularity of social media, studies that address its potential as a source of information for conservation and management of wildlife remain new and deserve special attention. Thus, in this study we aim to explore data from social media from the perspective of five different dimensions: what is it about, when was it generated, where was it generated, who generated it and engagement (i.e., public interaction with online content through metrics avaiable by social media) it received, in order to explore and learn from smaller data sets and apply it in automated processes. We obtained data from two search platforms: Facebook and Twiiter, related to four central species from brazilian wildlife: jaguar (Panthera onca), puma (Puma concolor), howler monkey (Alouatta spp.) and sloth (Bradypus spp.; Choloepus spp.). We use the combination of "species + local" search on Facebook and only "species" on Twitter through API (Application Programming Inteface) use. We obtained 317 posts for the species on Facebook and 38,516 on Twitter (with an estimated 10% of posts not corresponding to the species) on Twitter. We classified data in 12 categories, we observed that the most prominent categories were "sighting of fauna outside protected areas", "captivity", "rescue / treatment and release of wildlife" and "wildlife health". The specific analysis of the text by species revealed words mainly related to these categories on Facebook with the inclusion of terms related to the Pantanal biome and other areas on Twitter. We observed temporal patterns that highlight the importance of categories to understand information peaks on Facebook. On Twitter, temporal patterns seem to be related to the same categories found in Facebook, but we use word ranking to understand peaks of information. Words like "Juma" (jaguar shot dead before 2016 Brazil Olympic Games) were important in determining events that generated peaks in posting. In general, the spatial distribution of posts was concentrated in the municipality of SÆo Paulo with little data showing precise location of events. We found 9 categories of users types on Facebook, where personal pages, news pages, business and zoos and aquariums were the categories with most posts found. On Twitter, we observed a great variation in relation to the values obtained for followers and friends of users who posted about the species of interest in this study. When we analyze engagement variables online, we see a predominance of positive reactions on Facebook and high values for sharing and commenting on posts, with the exception of the howler monkey, who showed negative reactions. We identified the importance of topics such as yellow fever in determining engagement. In addition, we found variables with a positive association with engagement through multiple linear regression, such as "wildlife sighting in a protected area" and the type of user "government institution". Using machine learning algorithms, we obtained results varying between 0.58 and 0.71 of accuracy for the automated classification performed on Twitter database. The main conclusion of this work was the importance of using smaller data clusters to deal with large social network data sets in the context of species conservation using Brazil and the state of SÆo Paulo as areas of study. In addition, we found the need to expand research in this segment in Brazil that contribute to applied conservation. |
|
 |
PDF files are only accessible to Friends of the Cat Group. Joining Friends of the Cat Group gives you unlimited access and downloads in the Cat SG Library for one year, and allows you to receive our newsletter Cat News (2 regular issues per year plus special issues). More information how to join here |
(c) IUCN/SSC Cat Specialist Group ( IUCN - The World Conservation Union) |