Website


Senior Member of Technical Staff at Sandia National Labs
Ph.D. University of Illinois at Urbana-Champaign (Advisor: Prof. Les Gasser)
M.S. University of Illinois at Urbana-Champaign
B.S. Northern Illinois University

klakkara@gmail.com
klakkar@sandia.gov


"...well, Samuel rode lightly on top of a book and he balanced happily among ideas the way a man rides white rapids in a canoe. But Tom got into a book, crawled and groveled between the covers, tunneled like a mole among the thoughts, and came up with the book all over his face and hands."

From East of Eden, by John Steinbeck

I use Artificial Intelligence/Machine Learning (AI/ML) techniques and modeling and simulation (M&S) to better understand social phenomena. My work has spanned multiple domains, including linguistic diffusion, solar panel purchasing, cybersecurity technology adoption in organizations, the diffusion of norms and behaviors and conflict among nations.



News:
  • NEW: The book I co-edited with Prof. Gita Sukthankar and Prof. Rolf Wigand is coming out soon! It brings together an interdisciplinary set of papers on social interaction in games, particularly Massively Multiplayer Online Games. Check it out here:
book website

  • Our paper was accepted as a full paper at: SBP 2016: "Leveraging Network Dynamics for Improved Link Prediction"Alireza Hajibagheri, Gita Sukthankar, Kiran Lakkaraju
  • My paper on the Multi-Agent Multi-Attitude model was accepted for publication in the "Social Network Analysis and Mining" (SNAM) journal!
  • My paper was accepted for a poster presentation at AAMAS 2015: "

    Reducing diffusion time in attitude diffusion models through agenda setting.

    "
    Kiran Lakkaraju
  • Our paper was accepted for oral presentation at AAMAS 2015: "

    Data-Driven Agent-Based Modeling, with Application to Rooftop Solar Adoption

    "
    , Haifeng Zhang, Yevgeniy Vorobeychik, Joshua Letchford, Kiran Lakkaraju
  • The book I co-edited with Fernando Koch and Felipe Meneguzzi just came out. It contains papers from our 2014 AVSA workshop held as a part of AAMAS 2014. 
http://link.springer.com/book/10.1007%2F978-3-662-46241-6

  •  Our paper was accepted for oral presentation at SBP 2015: "Conflict and Communication in Massively-Multiplayer Online Games", Alireza Hajibagheri, Kiran Lakkaraju, Gita Sukthankar, Rolf Wigand, Nitin Agarawal. 
  • My paper on sample composition on MTurk was accepted for the poster session at SBP 2015: "A study of daily sample composition on Amazon Mechanical Turk", Kiran Lakkaraju
  • Our paper on the CLOSE platform was accepted for the poster session at SBP 2015: "The Controlled, Large, Online Social Experimentation Platform", Kiran Lakkaraju, et. al. 
  • Awrad Ali will be giving a talk at the ASE BigData/Social Informatics conference on our paper: "Synthetic Generators for Cloning Social Network Data", Awrad Mohammed Ali, Hamidreza Alvari, Alireza Hajibagheri, Kiran Lakkaraju and Gita Sukthankar
  • I'm giving a talk on the "Controlled, Large, Online Social Experimentation (CLOSE)" platform at the the Conference on Digital Experimentation (http://codecon.net/) on Saturday, October 11th, 2014!
  • I'm giving a talk at the University of Texas - Austin's Energy Symposium on Thursday, October 9th, 2014!
  • I'm organizing the Energy Market Prediction (EMAP) Symposium as part of the AAAI Fall Symposium Series (with Eugene Vorobeychik and Adam Cohen)
  • Our demo paper was accepted for the demo track at AAMAS 2014: Robert G. Abbott, Kiran Lakkaraju, Christina Warrender, "Semi-Automated Construction of adversarial agents for trainable-automated forces". See a video here. 
  • Our paper was accepted for oral presentation at SBP 2014: Jina Lee and Kiran Lakkaraju, "Predicting Social Ties in Massively Multiplayer Online Games" 
  • Our paper was accepted as a Poster at SBP 2014: Alvari, Lakkaraju, Sukthankar, Whetzel, "An Analysis of Guild Composition in Massively Multiplayer Online Games"
  • I'm organizing the Workshop on Agents, Virtual Societies and Analytics (AVSA 2014) at AAMAS 2014 in Paris, France!

Working Papers:

   Amazon Mechanical Turk (AMT) has become a powerful tool for social scientists due to its inexpensiveness, ease of use, and ability to attract large numbers of workers. While the subject pool is diverse, there are numerous questions regarding the composition of the workers as a function of when the “Human Intelligence Task” (HIT) is posted. Given the “queue” nature of HITs and the disparity in geography of participants, it is natural to wonder whether HIT posting time/day can have an impact on the population that is sampled. We address this question using a panel survey on AMT and show (surprisingly) that except for gender, there is no statistically significant difference in terms of demographics characteristics as a function of HIT posting time.
Posted on SSRN here.

Activities:



Updated: 8/1/2018