Skip to main content

Currently Skimming:

Appendix B Social Behavioral Modeling
Pages 64-73

The Chapter Skim interface presents what we've algorithmically identified as the most significant single chunk of text within every page in the chapter.
Select key terms on the right to highlight them within pages of the chapter.


From page 64...
... Traditional social network analysis centers on relatively simple networks. A typical social network analysis works with a single network connecting people to people by some SOCIAL NETWORK MODELS relationship (perhaps they work together)
From page 65...
... ing techniques are combined with machine learning to en- This area builds on social network analysis and link analysis able rapid database transformation and pattern extraction. and adds computer simulation to the mix to look at network Much of the work in this area has focused on the identifica- evolution.
From page 66...
... Most metrics have received some level of validation or ing network analysis. Social network analysis, link analysis, verification.
From page 67...
... or lower than another node on some metric or comparing the Finally, from a defense perspective, network analysis metrics related to two data sets. However, there are no abso- tools have to take into account multimode, multilink data.
From page 68...
... Thus, you are likely to see an As noted, these classification factors are the common di- MAS with a few very sophisticated agents and an MAS mensions along which MASs vary: with many cognitively trivial agents. When the agents are cognitively sophisticated, the cognitive model of · Number of agents.
From page 69...
... In contrast, most MASs representing humans to interact with agents representing with millions of cognitively simple agents, particularly companies or with agents representing institutions, the basic those built in the MAS frameworks, do not model real communication, learning, and behavioral features are not social networks or groups but may differentiate actors available. Such multigranular models can be built in these on anywhere from two to five sociodemographic di- frameworks; however, it is often more complex than build mensions.
From page 70...
... generate. A side product is that the addition of empirically MASs using cognitively sophisticated agents tend to rebased rules and equations often increases the plausibility of quire the use of knowledge engineering techniques.
From page 71...
... The devel 1 opment of MAS frameworks and the explosion of network These fields include anthropology, sociology, psychology, organiza tion science, marketing, physics, electrical engineering, ecology, biology, analytic tools is making social behavioral modeling widely bioinformatics, health services, forensics, artificial intelligence, robotics, available and is leading to the development of many small, computer science, mathematics, statistics, information systems, medicine, single-purpose tools. If they are to be fully explorted, they civil engineering, and communications.
From page 72...
... Such technology would facilitate faster processing the use of the MAS to provide flexible opponents and/or to and enable more real-time solutions, particularly for large- make the apparent number of game players larger and so scale networks. force players to think about group scale issues, the ability to To reduce the qualitative aspect of interpretation in this track and analyze behavior using dynamic network analysis field, a living archive of collected network data is needed, techniques, and the use of these games to generate data to replete with information on metrics for the nodes in each test tools.
From page 73...
... degree programs is vital to our national intellectual strength These activities would increase the maturity of this field, if we are to remain at the forefront in this area and to have a improve scientific theory, facilitate rapid linking of models stronger workforce of computational social analysts capable to solve novel problems, and encourage new discoveries. of developing and using social behavioral models.


This material may be derived from roughly machine-read images, and so is provided only to facilitate research.
More information on Chapter Skim is available.