Dynamic Targeting in an Online Social Medium

Abstract

Abstract. Online human interactions take place within a dynamic hierarchy, where social influence is determined by qualities such as status, eloquence, trustworthiness, authority and persuasiveness. In this work, we consider topic-based Twitter interaction networks, and address the task of identifying influential players. Our motivation is the strong desire of many commerical entities to increase their social media presence by engaging positively with pivotal bloggers and tweeters. After discussing some of the issues involved in extracting useful interaction data from a Twitter feed, we define the concept of an active node subnetwork sequence. This provides a time-dependent, topic-based, summary of relevant Twitter activity. For these types of transient interactions, it has been argued that the flow of information, and hence the influence of a node, is highly dependent on the timing of the links. Some nodes with relatively small bandwidth may turn out to be key players because of their prescience and their ability to instigate follow-on network activity. To simulate a commercial application, we build an active node subnetwork sequence based on key words in the area of travel and holidays. We then compare a range of network centrality measures, including a recently proposed version that accounts for the arrow of time, with respect to their ability to rank important nodes in this dynamic setting. The centrality rankings use only connectivity information (who Tweeted whom, when), but if we post-process the results by examining account details, we find that the time-respecting, dynamic, approach, which looks at the follow-on flow of information, is less likely to be 'misled' by accounts that appear to generate large numbers of automatic Tweets with the aim of pushing out web links. We then benchmark these algorithmically derived rankings against independent feedback from five social media experts who judge Twitter accounts as part of their professional duties. We find that the dynamic centrality measures add value to the expert view, and indeed can be hard to distinguish from an expert in terms of who they place in the top ten. We also highlight areas where the algorithmic approach can be refined and improved.

A year in Madrid as described through the analysis of geotagged Twitter data

“…A significant amount of analysis can be performed on tweets without location information, for example, with keyword and keyphrase extraction using probabilistic models (Zhao et al, 2011), or modeling the full structure of tweets in Twitter conversations (Ritter et al, 2010). The interaction between users can be analyzed to predict ''re-tweeting'' behavior (when a user broadcasts another user's tweet) (Suh et al, 2010), or to find important users responsible for influencing the twitter network (Laflin et al, 2012). With location information, many other lines of investigation are available.…”

Evolving HMM for ranking Twitter influence

“…[1] and [11] have considered the dynamic behavior of a twitter user which changes over time. [11] have captured this dynamic behavior of a user by focusing on a subnetwork on which user is active which is also topic based, subject matter experts identify the accounts that are most active in a particular topic and that is studies; model used is making of the same network as the user and its connected user then determining the probabilities of each path.…”