The AAAI 2012 Fall Symposium on Machine Aggregation of Human Judgment focuses on combining human and machine inference. For unique events and data-poor problems, there is no substitute for human judgment. Even for data-rich problems, human input is needed to account for contextual factors. For example, textual analysis is data rich, but context and semantics often make automated parsing unusable. However, humans are notorious for underestimating the uncertainty in their forecasts and even the most expert judgments exhibit well-known cognitive biases. The challenge is therefore to aggregate expert judgment such that it compensates for the human deficiencies.

There are fundamental theoretical reasons to expect aggregated estimates to out-perform individual forecasts. These theoretical results are borne out by a robust empirical literature demonstrating the superiority of opinion pools and prediction markets over individual forecasts, and of ensemble forecasts over those of top models. While weighted forecasts are theoretically optimal, among human experts unweighted forecasts have been hard to beat.

This symposium focuses on methods with the potential to come closer to the theoretical optimum. While a number of methods have shown promise individually, there is potential for significant advancement from combining them into structured, efficient, repeatable elicitation and aggregation protocols. Benefits of improved aggregation methods include substantial increases in the quality and reliability of expert judgements, removing misunderstanding, illuminating context dependence of forecasts, and reducing overconfidence and motivational bias in forecasts. On the other hand, there’s some skepticism that statistical models can outperform experts most of the time. Machine reasoning lacks the context to know when the models no longer apply, or in cases like natural language, simply lack sufficient context to be reliable in open-world or novel problems. This symposium considers powerful hybrid techniques using humans to help aggregate computer models.

A broad range of researchers in the AI community and other application fields such as econometrics, sociology, political science, and intelligence analysis will find this symposium interesting and useful. Bringing these disciplines together to the venue also greatly facilitates the research endeavors.

Format
The symposium will accept a number of regular papers (6-8 pages), and short papers/extended abstracts (2 pages). In addition to oral presentations, we intend to provide several poster sessions for more interactions. Further, invited talks by leading researchers in the fields and/or domain experts will be arranged. We will also reserve substantial time for questions and discussions after talks.

Topics include but not limited to the following
• Reasoning under uncertainty
• Ensembles & aggregation
• Information fusion
• Crowdsourcing techniques & applications
• Information elicitation & presentation
• Performance evaluation: scalability and accuracy
• Prediction markets
• Collective intelligence
Submission
Submission should be done through EasyChair submission site. Authors, who do not have accounts on EasyChair, will be directed to create a new account before they can make submission.

Important Dates
• Friday, May 25, 2012, 11:59pm Eastern Time – Papers/abstracts due.
• Friday, June 22, 2012 – Author notification of acceptance/rejection.
• Friday, September 07, 2012 – Camera-ready paper due.
• Friday November 02 – Sunday November 04, 2012 – Symposium at Arlington, Virginia.

Organizing Committee
Kathryn B. Laskey, Wei Sun (George Mason University), John Irvine (Draper Laboratory), Dirk B. Warnaar (Applied Research Associates, Inc.), H. Van Dyke Parunak (Jacobs Technology Inc.)

Supplementary Website
For more information about the symposium, and for submission guidelines and links, please visit the supplementary website (http://magg.c4i.gmu.edu).