Overview
Social media today provide an impressive amount of data about users and their societal interactions, thereby offering computer scientists, social scientists, economists, and statisticians many new opportunities for research exploration. Arguably one of the most interesting lines of work is that of forecasting future events and developments based on social media data, as we have recently seen in the areas of politics, finance, entertainment, market demands, health, etc.

But what can successfully be predicted and why? Since the first algorithms and techniques emerged rather recently, little is known about their overall potential, limitations and general applicability to different domains.

Better understanding the predictive power and limitations of social media is therefore of utmost importance, in order to, for example, avoid false expectations, misinformation or unintended consequences. Today, current methods and techniques are far from being well understood, and it is mostly unclear to what extent or under what conditions the different methods for prediction can be applied to social media. While there exists a respectable and growing amount of literature in this area, current work is fragmented, characterized by a lack of common evaluation approaches. Yet, this research seems to have reached a suficient level of interest and relevance to justify a dedicated special issue.

This special issue aims to shape a vision of important questions to be addressed in this field and fill the gaps in current research by soliciting presentations of early research on algorithms, techniques, methods and empirical studies aimed at the prediction of future or present events based on user generated content in social media.

Topics
To address this guiding theme the special issue will be articulated around, but not limited to, the following topics:

1. Politics, branding, and public opinion mining (e.g., electoral, market or stock market prediction).
2. Health, mood, and threats (e.g., epidemic outbreaks, social movements).
3. Methodological aspects (e.g., data collection, data sampling, privacy and data de-identification).
4. Success and failure case studies (e.g., reproducibility of previous research or selection of base-lines).

Schedule
- Manuscript due date: June 1, 2012
- Decisions due: August 1, 2012
- Revised paper due: September 15, 2012
- Notification of acceptance: October 1, 2012
- Submission of final manuscript: October 31, 2012
- Publication date: late 2012 / early 2013 (tentative)

Submission
All submitted manuscripts should be original contributions and not be under consideration in any other venue.

Publication of an enhanced version of a previously published conference paper is possible if the review process determines that the revision contains significant enhancements, amplification or clarification of the original material. Any prior appearance of a substantial amount of a submission should be noted in the submission letter and on the title page.

Submissions must adhere to the Author Guidelines available at:
http://www.emeraldinsight.com/products/journals/author_guidelines.htm?id=intr
Detailed instructions will be announced later this year.

Guest editors
- Daniel Gayo-Avello [@PFCdgayo], University of Oviedo (Spain), dani@uniovi.es
- Panagiotis Takis Metaxas [@takis_metaxas], Wellesley College and Harvard University (USA), pmetaxas@seas.harvard.edu
- Eni Mustafaraj [@enimust], Wellesley College (USA), emustafa@wellesley.edu
- Markus Strohmaier [@mstrohm], Graz University of Technology (Austria), markus.strohmaier@tugraz.at
- Harald Schoen, University of Bamberg (Germany), harald.schoen@uni-bamberg.de
- Peter Gloor [@pgloor], MIT (USA), pgloor@mit.edu

Feel free to contact the guest editors if you have any question.

In his inaugural lecture “The End of the Virtual: Digital Methods” Richard Rogers who holds the Chair of New Media & Digital Culture at the University of Amsterdam proposes a shift in internet research:

“The issue no longer is how much of society and culture is online, but rather how to diagnose cultural change and societal conditions using the Internet.”
Rogers: The End of the Virtual. p. 8

For Rogers too much of research focuses on the differences between on- and offline culture. He sees the reason for this in the methods with which researchers from the humanities and the social sciences approach the internet. Rogers’ critiques the use of surveys, interviews and other approaches that proved succesfull in offline research. He collects these methods under the term virtual methods. To him the exclusive use of these virtual methods leads to an unnessary concentration of research on just a few topics and would even mislead in the quest to advance our understanding the internet.

“The argument advanced here is that virtual methods and user studies in the social sciences and the humanities have shifted the attention away from the data of the medium, and the opportunities for study of far more than online culture.”
Rogers: The End of the Virtual. p. 6

To remedy this situation Rogers advances the notion of methods based on online groundedness. Instead of imposing research approaches from differenct context on internet research he proposes a research approach that uses the epistemology of the internet as methodological basis. Rogers calls these methods digital methods:

“For the third era of Internet research, the digital methods program introduces the term online groundedness, in an effor t to conceptualize research which follows the medium, captures its dynamics, and makes grounded claims about cultural and societal change. Indeed, the broader theoretical goal of digital methods is to rethink the relationship between the Web and the ground.”
Rogers: The End of the Virtual. p. 8

Rogers suggests that through the use of digital methods we will be able to use the internet as a data source that informs on social processes offline that until now remained hidden.

“The conceptual point of departure for the research program is the recognition that the Internet is not only an object of study, but also a source. Knowledge claims may be made on the basis of data collected and analyzed by devices such as search engines. [...] It thereby challenges existing methods of data collection [...], and reopens the discussion of the Web as anticipatory medium, far closer to the ground than one might expect.”
Rogers: The End of the Virtual. p. 8

Rogers then moves on and discusses a group of epistemological elements of the interent that can serve as basis for research using digital methods. These elements are The Link, The Website, The Search Engines & the Spheres, The Webs, Social Networking Sites & Post-demographics, and Wikipedia & Networked Content. For each element he discusses recent research and further research possibilities.

Rogers’ text is a welcome addition to the developing debate about computational social science. While the manifesto Computational Social Science by the luminaries of the field David Lazer, Alex Pentland, Lada Adamic, Sinan Aral, Albert-László Barabási, Devon Brewer, Nicholas Christakis, Noshir Contractor, James Fowler, Myron Gutmann, Tony Jebara, Gary King, Michael Macy, Deb Roy, and Marshall Van Alstyne opens up a promising research field there are also real dangers lurking. Be it data driven web sience, digital methods, analysis of social networks, or computational social science, these field are blessed by an ever increasing amount of data. While the best research in these fields does not forget theory, the more data we get the louder the voices become that proclaim the end of theory: All theory has become obsolete. The truth is in the data all apparent to mighty algorithms. For an example of such an argument see Chris Anderson’s unfortunate essay The End of Theory: The Data Deluge Makes the Scientific Method Obsolete. Rogers’ text offers a welcome example how to combine theory and data.

Rogers’ text is also a timely reminder that there is more to a science of the web than just the analysis of opportunity data sets. The richness of data collected on Twitter or Facebook can serve as basis for original research (for an example of an analysis based on data sets collected on Twitter see for example Drew Conway’ s post “SNA in R Talk, Updated with [Better] Video “; for research based on Facebook data sets see “How to split up the US” by Pete Warden). In the short term analyses like these can provide original and valuable insights. Still, if this research is not conducted in a larger research context we risk losing sight of the bigger picture.

But Roger’s text does not only offer interesting perspectives to researchers coming from a data perspective. “The End of the Virtual” also offers an interesting advancement to researchers coming from the humanties or the social sciences. Rogers directs their focus away from shiny “new” phenomena on the web towards the data structure behind these phenomena. This might curb the enthusiasm of some research but at the same time advance our knowlegde about the web at large and the conditions of social action online.

The End of the Virtual can be found either in bookform here or a pre-print of the lecture as pdf on Richard Rogers’ website.

Disclaimer: Richard Rogers sent me a free copy of his “The End of the Virtual”.