Analyzing the Dynamic Evolution of Hashtags on Twitter: a Language-Based Approach

Abstract

Hashtags are used in Twitter to classify messages, propagate ideas and also to promote specific topics and people. In this paper, we present a linguistic-inspired study of how these tags are created, used and disseminated by the members of information networks. We study the propagation of hashtags in Twitter grounded on models for the analysis of the spread of linguistic innovations in speech communities, that is, in groups of people whose members linguistically influence each other. Differently from traditional linguistic studies, though, we consider the evolution of terms in a live and rapidly evolving stream of content, which can be analyzed in its entirety. In our experimental results, using a large collection crawled from Twitter, we were able to identify some interesting aspects – similar to those found in studies of (offline) speech – that led us to believe that hashtags may effectively serve as models for characterizing the propagation of linguistic forms, including: (1) the existence of a “preferential attachment process”, that makes the few most common terms ever more popular, and (2) the relationship between the length of a tag and its frequency of use. The understanding of formation patterns of successful hashtags in Twitter can be useful to increase the effectiveness of real-time streaming search algorithms. to the topic of the message. They can be used not only to add context and metadata to the posts, but also for promotion and publicity. By simply adding a hash symbol (#) before a string of letters, numerical digits or underscore signs (_), it is possible to tag a message, helping other users to find tweets that have a common topic. Hashtags allow users to create communities of people interested in the same topic by making it easier for them to find and share information related to it (Kricfalusi, 2009). Figure 1 shows an example of query for the tag “#basketball”, which returns the newest tweets with this hashtag. 1