Abstract
The Human Dynamics research group is developing methods to automatically map the flow of information within groups and communities using audio collected from wearable sensors such as mobile phones or PDAs. Computational models of group interaction dynamics are then derived from this data, allowing us to answer questions such as: Who influences whom? How much? How can we modify group interactions to promote better information diffusion? The goal is real-time learning and modification of information flow within organisations; we describe initial results and discuss concerns about user privacy.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Gladwell M: 'The tipping point: how little things make can make a big difference', New York: Little Brown (2000).
Huberman B and Hogg T: 'Communities of practice: performance and evolution', Computational and Mathematical Organisation Theory, 1, pp 73—95 (1995).
Allen T J: 'Managing the flow of technology', MIT Press, Cambridge, MA (1977).
Cohen D and Prusak L: 'In good company: how social capital makes organisations work', Harvard Business School Press, Cambridge, MA (2001).
Oliver N, Rosario B and Pentland A: 'A Bayesian computer vision system for modeling human interaction', IEEE Transactions on Pattern Analysis and Machine Intelligence, 22, No 8, pp 831—843 (2000).
Asavathiratham C: 'The influence model: a tractable representation for the dynamics of networked Markov chains', PhD Thesis in Dept of EECS, MIT (2002).
Gerasimov V, Selker T and Bender W: 'Sensing and effecting environment with extremity computing devices', Motorola Offspring, 1, No 1 (2002).
DeVaul R, Sung M, Gips J and Pentland A: 'Applications and architecture', Proceedings IEEE Intl Sym on Wearable Computing, White Plains, NY (2003) — available as MIT Media Laboratory Technical Note No 567 — http://hd.media.mit.edu
Choudhury T and Clarkson B: 'Reference design for a social interaction sensing platform', Media Laboratory Internal Design Document, Cambridge, MA (2002).
Choudhury T and Pentland A: 'Sensing and modeling human networks using the sociometer', Proceedings of the International Conference on Wearable Computing, White Plains, NY (October 2003) — available MIT Media Laboratory Technical Note No 564 — http://hd.media.mit.edu
Choudhury T: 'Sensing and modeling human networks', PhD Thesis, Dept of Media Arts and Sciences, MIT (2003).
Choudhury T and Pentland A: 'Characterising social networks using the sociometer', Proc NAACOS, Pittsburgh, PA, Kluwer (June 2004) — available as MIT Media Laboratory Technical Note No 569 — http://hd.media.mit.edu
Eagle N and Pentland A: 'Social network computing', IEEE Conference on Ubiquitous Computing (UbiComp), Seattle, WA (October 2003) — available as MIT Media Laboratory Technical Note No 580 — http://hd.media.mit.edu
Eagle N and Pentland A: 'Social serendipity: proximity sensing and cueing', MIT Media Laboratory Technical Note No 570 (2004) — http://hd.media.mit.edu
Jebara T, Ivanov Y, Rahimi A and Pentland A: 'Tracking conversational context for machine mediation of human discourse', in AAAI Fall 2000 Symposium: 'Socially Intelligent Agents: The Human in the Loop', (November 2000) — available as MIT Media Laboratory Technical Note No 530 — http:// hd.media.mit.edu
Eagle N, Singh P and Pentland A: 'Commonsense conversations: understanding casual conversation using a commonsense database', Mobile Computing Workshop, IJCAI, Acapulco, MX (2003) — available as MIT Media Laboratory Technical Note No 562 — http://hd.media.mit.edu
Basu S: 'Conversation scene analysis', PhD Thesis in Dept of Electrical Engineering and Computer Science, MIT (2001).
Schafer R D: 'An introduction to nonassociative algebras', New York, Dover (1996).
Basu S, Choudhury T, Clarkson B and Pentland A: 'Learning human interactions with the influence model', MIT Media Laboratory Technical Note No 539 (2001) — http:// hd.media.mit.edu
Blimes J: 'A gentle tutorial on the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models', University of California, Berkley (1997).
Lauritzen S L and Spiegelhalter D J: 'Local computations with probabilities on graphical structures and their application to expert systems', Journal of the Royal Statistical Society, B50, pp 157— 224 (1988).
Bertsekas D P: 'Nonlinear programming', Belmont, Athena Scientific (1995).
Pentland A: 'Social dynamics: the voice of power and influence', MIT Media Laboratory Technical Note No 579 (2004) — http:// hd.media.mit.edu
Mandan A, Caneel R and Pentland A: 'Towards socially intelligent wearable networks', MIT Media Laboratory Technical Note No 583 (2004) — http://hd.media.mit.edu
Pentland A, Curhan J, Eagle N and Martin M: 'Money and influence', MIT Media Laboratory Technical Note No 577 (2004) — http://hd.media.mit.edu
Sung M, Gips J, Eagle N, Madan A, Caneel R, DeVaul R, Bonsen J and Pentland A: 'MIT.EDU: M-learning applications for classroom settings', Proc IEEE WMTE, Jungli Taiwan (2004) — available as MIT Media Laboratory Technical Note No 576 — http:// hd.media.mit.edu
About this article
Cite this article
Pentland, A. Learning Communities — Understanding Information Flow in Human Networks. BT Technology Journal 22, 62–70 (2004). https://doi.org/10.1023/B:BTTJ.0000047584.04959.18
Issue Date:
DOI: https://doi.org/10.1023/B:BTTJ.0000047584.04959.18