Nov 30: Steven Johnson to present on The strength of words online: Emergent leadership in online communities

Steven Johnson
Assistant Professor, MIS
Fox School of Business, Temple University

November 30, 2012
Speakman Hall 200, 1000am – 1100am
Seminar Title : The strength of words online: Emergent leadership in online communities

Compared to traditional organizations, online communities lack formal power or leadership positions. Instead, leadership in online communities is an emergent process resulting from influencing others. The objective of this paper is to investigate how network structure and language usage lead to influence in online communities. Communication online occurs almost exclusively through written words. The study of online influence has been dominated by a focus on structural network position with surprisingly little research addressing how the comparative use of language shapes community dynamics. Using participant surveys to identify influential members, this study analyzes a year of network history and message content to identify if leader utterances have unique qualities compared to the utterances of other core community members. Analysis supports the conclusion that online leadership derives from more than network position; it is also associated with distinctive written communication patterns. The composite view of emergent leaders in online communities is: they are in a central, core position in a network; they concentrate participation in fewer message threads than others; and, they provide a large number of positive, concise posts that include an above average number of external links and use simple language familiar to other participants. Online community leaders emerge through both the context and content of online communication.

Please email for a copy of the paper

Feb 25: Steven Johnson to speak on How do power law distributions arise in online communities?

Steven Johnson

Assistant Professor,
Fox School of Business,
Temple University

February 25, 2011

Speakman Hall 200, 1000am – 1130am

Seminar Title : How do power law distributions arise in online communities?


Power law rank/frequency distributions appear ubiquitous in online communities but the mechanisms of their formation are not well understood. This study models online communities and multiple network formation mechanisms that can lead to the emergence of power distributions. First, we establish the presence of power law distributions in twenty-eight online communities. Next, we develop a simulation model of the formation of thread-based asynchronous online communities and provide results based on over 4,500 runs of the model simulating a total of over 3,200,000 messages generated by over 340,000 participants. Finally, we evaluate if these network formation models generate simulated networks with power law distributions. To validate that these models are consistent with the observed networks we use multiple measures of network structure: the power law distribution degree, network density, mutuality index and clustering coefficient. This study contributes to our understanding of online communities and other social communication networks by illuminating the relationships between specific behavioral tendencies of participants and emergent structural network characteristics.

We find no evidence that preferential attachment explains the presence of power laws in online communities but instead that a generalized social exchange mechanism is the participant behavior most consistent with observed power laws.

Please email me for a copy of the full paper (

Feb 18: Ramayya Krishnan to speak on Dynamics of Network Structure and Content in Social Media

Ramayya Krishnan

Dean of Heinz College
H. John Heinz III Dean and W. W. Cooper and Ruth F. Cooper Professor of Management Science and Information Systems
Heinz College, Carnegie Mellon University

February 18, 2011

Speakman Hall 200, 1000am – 1130am

Krishnan will present two papers related to social media . In addition, he will discuss the open problem of how one should think about privacy protection of network data using a decision-theoretic approach of trading off data utility with disclosure risk

Title 1: Dynamics of Network Structure and Content in Social Media

Abstract 1

Organizations use social media to leverage knowledge contributions by individual employees, which also foster social interactions { activity in blogs, forums, wikis etc. is critical to ensuring a thriving online community. Prior studies have examined contributions to such media at the level of the individual, focusing on drivers of participation, whereas we investigate three different dimensions of dyadic interactions. Our setting is an online forum in an enterprise, where employees both exchange knowledge by query-response and interact socially.
Using a networks approach to query-response behavior, we characterize each interaction as a directed tie, and view the entire set of online forum interactions as a social network. We evaluate network constructs including Simmelian embeddedness and content of relationships (expressive or instrumental), to understand the mechanisms underlying online social interactions.
We find that content and embedded nature of the relationship strongly influence responses: Simmelian ties formed in an expressive setting have the highest positive impact on response propensity, i.e. both content and embeddedness are impactful and reinforce each other. Our results have implications for designing online social communities, specifically that practitioners ought to consider the benefits of purely social interactions through the forum that may serve to lubricate future instrumental interactions.

Title 2:  Homophily or Influence? An Empirical Analysis of Purchase within a Social Network

Abstract 2

Consumers that are close to one another in a social network are known to have similar behaviors. The focus of this study is the extent to which such observed similarity is driven by homophily or social influence. Homophily refers to the similarity in product preferences between individuals who are connected. Social influence is the dependence of consumers’ purchase decisions on their communication with others. We construct a hierarchical Bayesian model to study both the timing and choice of consumer purchases within a social network. Our model is estimated using a unique social network dataset obtained from a large Indian telecom operator for the purchase of caller ringer-back tones. We find strong social influence effects in both the purchase-timing and product-choice decisions of consumers. In the purchase-timing decision, we find that consumers are three times more likely to be influenced by network neighbors than by other people. In the product-choice decision we find a strong homophily effect. We show that ignoring either homophily or social influence will result in overestimated effects of the other factor. Furthermore, we show that detailed communication data is crucial for measuring influence effect, and influence effect can be either over- or underestimated when such data is not available. Finally, we conduct policy simulations on a variety of target marketing schemes to show that promotions targeted using network information is superior. For example, we find a 4-21% improvement on purchase probability, and an 11-35% improvement for promoting a specific product.

For a copy of the paper1, click here.

For a copy of the paper2, click here.