دانلود رایگان مقاله انگلیسی محل کاوی از رسانه های اجتماعی: بررسی سیستماتیک - الزویر 2018

ABSTRACT

During the last ten years, a large body of research extracting and analysing geographic data from social media has developed. We analyse 690 papers across 20 social media platforms, focussing particularly on the method used for extraction of location information. We discuss and compare extraction methods, and consider their accuracy and coverage. While much work has adopted location information in the form of coordinates in message metadata, this approach has very limited coverage in most platforms and reports on posting location rather than message location or the location that the message refers to (geofocus). In contrast, a wide array of other approaches have been developed, with methods that extract place names from message text providing the highest accuracy. Methods that use social media connections also provide good results, but all of the methods have limitations. We also present analysis of the range and frequency of use of different social media platforms, and the wide range of application areas that have been addressed. Drawing on this analysis we present a number of future areas of research that warrant attention in order for this field of research to mature.

Conclusions

The potential of social media as a source of geographic data that is not currently available, or as an alternative to more conventional data collection methods has been recognised by researchers since social media platforms became popular. A wide range of research has been generated that attempts to extract data of this kind, and in particular, to determine an accurate location of messages, users or topics discussed in messages. The most common method (MML), which uses coordinates that are contained in the message metadata, is very limited in coverage, and in some cases (if automatically extracted from the device) contains the location at which the message was posted, which may not necessarily be the geofocus of the message. Other methods that have received some attention and that give the best accuracy include MCN (which extracts place names from the message) and SNC (which uses social contacts to other users to establish location). MCN in particular can be effective in determining location using street names and building names, but relies on a well-developed gazetteer, and on users referring to relevant toponyms in their messages. Twitter is by far the most frequently used social media platform for geospatial research, despite being only 11th in global rankings by number of users, and research on more popular platforms (e.g. Facebook) is much more limited. There is a need for research into some of these less frequently used platforms, including the analysis of the location of content of particular kinds across and within the platforms. Geographic data has been extracted from social media across a vast range of application areas, from health to travel to politics, demonstrating the significant potential of the approach in collecting geographic data. The time has come to develop more comparable measures of quality of the methods that have been developed to extract location content, including a more standardised approach to the reporting of accuracy and coverage, that can enable researchers who are not experts in social media to better evaluate and employ the methods for location extraction that have been developed. It is currently very difficult for researchers who wish to apply social media data to a specific research question from some application domain to determine the best approach to use to extract geographic data, to evaluate the limitations of alternative approaches, and then to use the methods for their own research, and we assert that geographic data from social media could be used much more widely if this situation were addressed.