An integrated approach for cetacean knowledge and conservation in the central Mediterranean Sea using research and social media data sources

1. Sources of data other than those derived from conventional research protocols may contribute valuable information to fill gaps in knowledge about cetacean occurrences and diversity in a given area and help address conservation issues. 2. The performance of a method to examine cetacean communities based on presence records systematically derived from shared photographs and videos posted by boaters and maritime operators on social media (e.g. YouTube and Facebook) combined with patchy distributed visual/acoustic data collected by researchers has been evaluated. 3. Records (N = 1,274) gathered over a 10‐year period (2008–2017) have been used to obtain insights into species' presence and habitat selection in a scattered study area of the central Mediterranean Sea (Italy). The effectiveness of the method, practical and theoretical advantages, limitations, and challenges of using data originated from social media for research and conservation purposes are discussed. 4. Seven out of the eight cetacean species regularly residing in the Mediterranean have been reported in the area, with different relative densities. Maximum entropy modelling techniques have been applied to the datasets derived from (a) social media, (b) research surveys, and (c) the combination of the two, using six fixed variables as proxies for cetacean presence. Distance from the coast and depth emerged as the main variables predicting encounters, with specificities related to the ecology of the species. 5. The approach was reliable enough to obtain broad‐scale, baseline information on cetacean communities in the region, on the basis of which initial conservation recommendations and future research programmes can be proposed. 6. With the increasing need for studying whale and dolphin population ecology coming from national/international directives, support from citizens to aid research may act as a practical, inexpensive solution to gathering extensive spatial–temporal data for regional‐scale monitoring and for the development of management priorities