News & Events
A sampling of projects on the May 6, 2014 program
The Social Media and Business Analytics Collaborative will host a symposium on Tuesday, May 6, 2014, at the Carlson School of Management. University of Minnesota scholars and industry leaders will meet to discuss new and ongoing research in social media, social computing, and big data analytics. The symposium will include various types of research, including analysis of existing data sets to answer questions, experimentation using the online social graph, advances in underlying techniques, and the design of social computing platforms.
In anticipation of the event, a preview of some of the projects faculty and students will discuss follows. Primary presenters are listed here; coauthors' names appear in the symposium program.
Wikipedia has had a transformative effect on computer science research; however, it remains difficult for software developers to leverage Wikipedia as a knowledge resource. Brent Hecht will present WikAPIdia, a software library that allows researchers and practitioners to incorporate Wikipedia-based intelligence into their studies and systems. WikAPIdia not only provides simple access to the key structures of Wikipedia (e.g., link graph, text models), it also includes easy-to-use implementations of state-of-the-art artificial intelligence algorithms that have been developed using Wikipedia data.
Demand for online privacy is at an all-time high. Sensitive to this, many online venues offer privacy controls that enable users to specify which pieces of their information are publicly visible. Gord Burtch explores the impact of these controls on user behavior in a randomized control trial at an online crowdfunding platform. The project demonstrates the competing effects privacy controls have on user behavior. The findings have various implications for the design of online platforms.
Using more than 150,000 hourly observations on prices and sales ranks for e-books and physical bestsellers, Joel Waldfogel estimates the price elasticities of demand for books at Amazon. Not surprisingly, e-books appear to be priced below the static profit maximizing levels. More surprisingly, physical book prices also fall substantially short of the static profit maximizing level two decades after Amazon’s launch. These findings raise questions for both policymakers and shareholders.
Despite high traffic levels, user engagement with Facebook business pages is surprisingly low. According to one source, only 1% of Facebook fans engage with the brand through posts or comments. Using lab experiments, text mining, and statistical modeling to analyze half a million Facebook posts, Ching Ren examines the challenge of building a vibrant brand community on Facebook, and the impact of Facebook world-of-mouth on brand evaluation. The findings provide practical guidance for companies to engage customers and manage social media conversations effectively.
Deviance in online systems can drive off users and tarnish the system’s public image. Kenneth Shores' project develops a metric to identify deviant players, and looks at the effects of interacting with deviant players, including effects on retention. Based on the ﬁndings, the authors suggest methods to better identify and counteract the negative effects of deviance.
What kinds of activity attract audience attention and reposting on social curation sites like Pinterest? Shuo Chang studies the extent to which users specialize in particular topics, homophily among users, and differences between female and male users. The findings suggest strategies both for users (e.g., strategies to attract an audience) and maintainers (e.g., content recommendation methods) of social curation sites.
The symposium program includes a range of research topics and findings. Join us May 6 to learn about the following projects: