In this paper we outline some of the challenges for social media analytics and -at the same time -challenge existing approaches to social media analysis. Specifically, we suggest that there is an unhelpful gulf between social scientific approaches, which offer rich theoretical and methodological understandings of the social; and computational approaches which offer sophisticated methods for data harvesting, interrogation and modelling. Brought together these approaches might meet the challenges facing social media analytics and produce a different order of understanding. We offer two preliminary examples of this synthesis in practice: first, we show how established computational tools might be harnessed to address theoretically grounded empirical questions about the social; and second we consider social theories might inspire the development of new methodological tools for social media analytics. In doing so, we aim to contribute to the development of interdisciplinary social media analytics with in a broader framework of Web Science.
The Web has grown to be an integral part of modern society offering novel ways for humans to communicate, interact, and share information. New collaborative platforms are forming which are providing individuals with new communities and knowledge bases and, at the same time, offering insights into human activity for researchers, policy-makers and engineers. On a global scale, the role of cultural and language barriers when studying such phenomena becomes particularly relevant and presents significant challenges: due to insufficient information, it is often hard to establish the cultural or language groups in which individuals belong, while there are technical difficulties in establishing the relevance and in analysing resources in different languages. This paper presents a framework to the end of addressing those issues by leveraging data on the use of Wikipedia. Resources available in different languages are explicitly correlated in Wikipedia along with time-stamped logs of access to its articles. This paper provides a framework to enable temporal page views in Wikipedia to be associated with specific geographic profiles. This framework is then used to examine the exchange of information between the English speaking and Chinese speaking localities and reports initial findings on the role of language and culture in diffusion in this context.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with đź’™ for researchers
Part of the Research Solutions Family.