Innovation in hyperlink and social media networks: Comparing connection strategies of innovative companies in hyperlink and social media networks

Abstract

This paper seeks to unveil how (geospatial) connection strategies associated with business innovation, differ between geolocated social media and hyperlink company networks. Thereby, we provide a first step towards understanding connection strategies of innovative companies on social media platforms. For this purpose, we build a hyperlink and Twitter follower network for 11,892 companies in the information technology (IT) sector and compare them along four dimensions. First, underlying network structures were assessed. Second, we asserted information flow patterns between companies with the help of centrality measures. Third, geographic and cognitive proximities of companies were compared. Fourth, the influence of company characteristics was examined through linear and logistic regression models. This comparison revealed, that on a general level the basic connection patterns of the hyperlink and Twitter network differ. Nevertheless, the geospatial dimension (geographic proximity) and the knowledge base of a company (cognitive proximity) appear to have a similar influence on the decision to connect with other companies on Twitter and via hyperlinks. Further, the results suggest that innovative companies most likely align their connection strategies across hyperlink and Twitter networks. Thus, business innovation might effect connection strategies across online company networks in a comparable manner.

Drowning in the Information Flood: Machine-Learning-Based Relevance Classification of Flood-Related Tweets for Disaster Management

“…One possibility is to extract explicitly georeferenced Tweets, most of which become geocodable via a "place" tag set by the user for the respective Tweet. Numerous studies have already shown that significant statements on geo-social phenomena can be derived from this selection [17][18][19][20][21]. A major difficulty, however, is reducing the large, rather unstructured amount of data for each use case, i.e., to consider only relevant Tweets.…”