Thanks to Scott Timcke for a pointer to this excellent article and great summary of how to game your impact factor. This is a timely discussion, not only for impact factor but even more important for the development of altmetrics (which could easily be even more susceptible to gaming). The potential for gaming needs to be addressed along with the development of the metrics, not only as a distortion in the metrics per se, but the impact of the need to score well in metrics in how people approach their research in the first place.
From Smeyers, P., and Burbules, N. C., (2011) How to Improve your Impact Factor: Questioning the Quantification of Academic Quality, Journal of Philosophy of Education 45(1) 1–17
Offers a solid critique of I.F. and bibliometrics in general.
BUT if you do want to know how to improve your I.F. then
"• Forget about society and education in general.
• Find a research area that is flourishing and blessed with a large number of ISI journals.
• Limit your research interest to a minute aspect that is distinctly associated with you, and which can be addressed empirically.
• While you need not limit yourself to quantitative methods, bear in mind that these are always to be preferred.
• If you can at all, avoid case studies.
• Look for friends with whom you can swap cites.
• Cite your own work often, and cite lots of articles from the journal in which you want to publish.
• Do good work by all means, but above all be sure to publish findings that are controversial and widely debated … Then sit back and watch your impact factor grow."