No abstract

Data and data management techniques increasingly permeate organizations and the contexts in which they are embedded. We conduct an empirical investigation of Last.fm, an online music discovery platform, with a view to unpacking the work of data and algorithms in the process of categorization. Drawing on Eleanor Rosch and her colleagues, we link the making of categories with the construction of basic objects that function as key filters or registers for perceiving and organizing the world and interacting with it. In contexts such as the ones we have studied, basic objects are made out of data rather than expert or community-based knowledge. In such settings, basic objects work as pervasive reality filters and as the entities on which other organizational objects and categories are built. As they diffuse, such objects and the categories they instantiate become naturalized, increasingly reconfiguring the social order of organizations and their environments as a data order. Once key organizational activities such as the making of objects and categorizing are rearranged by data and algorithms, organizations can no longer be framed as separate from the technologies they deploy.

The growing business expansion of social media platforms is changing their identity and transforming the practices of networking, data and content sharing with which social media have been commonly associated. We empirically investigate these shifts in the context of TripAdvisor and its evolution since its very establishment. We trace the mutations of the platform along three stages we identify as search engine, social media platform and end-to-end service ecosystem. Our findings reveal the underlying patterns of data types, technological functionalities and actor configurations that punctuate the business expansion of TripAdvisor and lead to the formation of its service ecosystem. We contribute to the understanding of the current trajectory in which social media find themselves as well as to the literature on platforms and ecosystems. We point out the importance of services that develop as commercially viable and constantly updatable data bundles out of diverse and dynamic data types. Such services are essential to the making of the complementarities that are claimed to underlie ecosystem formation.