Earlier this month I was invited to give a talk as part the Criminal Investigations and Network Analysis Center (CINA) Distinguished Speaker Series. As readers of the blog might expect, I chose to talk about how open data (e.g. OpenStreetMap, Twitter) can be utilized in agent-based models to study a variety of applications (many of which can be found over on my research page). The talk itself was entitled: "Utilizing Agent-based Models and Open Data to Examine the Movement of People and Information: A Gallery of Applications." Below you can read the brief abstract of the paper and if this peaks your interest, CINA recorded my talk and highlighted (short) version is given below (while the full talk can be found at: https://youtu.be/iIvSnE-IBZI).
Abstract:
Today we are awash with many new forms of open data (e.g. crowdsourced, social media), but we are still challenged with how individuals make decisions and how this leads to more aggregate patterns emerging. One way to explore how individuals make decisions, or are impacted by information and their resulting consequences, is via agent-based modeling. Agent-based modeling allows for simulating heterogenous actors and their decision-making processes within complex systems. Through a series of example applications ranging from the small-scale movement of pedestrians over seconds, to that of the movement of people over borders over hours and days, I will demonstrate how open data can be leveraged within the agent-based building process. Specifically, the examples will show that by focusing on individuals, or groups of individuals and the networks that connect them, more aggregate patterns emerge from the bottom up.
Cities are complex systems which are constantly changing because of the interactions between the
people and their environment. Such systems often go through several life cycles which are shaped by
various processes. These may include urban growth, sprawl, shrinkage, and gentrification. These
processes affect the urban land markets which in turn affect the formation of a city through feedback
loops. Through models we can explore such dynamics, populations, and the environments in which
people inhabit. The model proposed in this paper intends to simulate the aforementioned dynamics
to capture the effect of agents’ choices and actions on the city structure. Specifically, this model
explores the effect of gentrification on population density and housing values. The proposed model is
significant in its integration of ideas from complex systems theory which is operationalized within an
agent-based model stylized on urban theories to study gentrification as a cause of increased in land
values. The model is stylized on urban theories and results from the model show that the agents move
to and reside in properties within their income range, neighboring agents that have similar economic
status. The model also shows the role of gentrification by capturing both the supply and demand
aspects of this process in the displacement and immobilization of agents with lower incomes. This
is one of the first models that combines several processes to explore the life cycle of a city through
agent-based modeling.
Model graphical user interface at default settings.
Gentrification by demand in the 10th neighborhood of the inner-city.
Turning to our second paper which was presented as a poster, entitled "Modeling Social Networks in an Agent-Based Model of a Nuclear Weapon of Mass Destruction Event" we discussed our continuing work on disasters. Specifically our project on how people might react in an event of Nuclear Weapon of Mass Destruction (NWMD) in New York City when one integrates social networks into an agent-based model. In the paper we discuss preliminary results which demonstrate how we can integrate household social networks explicitly into a spatially explicit model. Furthermore we demonstrate and benchmark agent commuting patterns for the New York City Commuter Region with a sample population (as we show in one of the movies below) along with demonstrating agents initial reactions post NWMD detonation.
Abstract:
Connections between human beings often influence where people go and
how they behave, yet their representation as social networks are rarely
modeled as a factor of human behavior in agent-based models. Social
networks are increasingly being used to study human behavior in
disasters, and empirical work has shown that human beings prioritize the
safety of themselves and loved ones (i.e., households) before helping
neighbors and coworkers. In this poster, we briefly present our
agent-based model being used to characterize the New York City area
population’s reaction to a Nuclear Weapon of Mass Destruction (NWMD)
event. The model methodology demonstrates how social networks can be
integrated into an agent-based model and act as a basis for
decision-making during a disaster. Preliminary simulations show how
agents potentially respond to a NWMD event with measurable changes in
location and network formations over space and time.
Keywords:
Agent-Based Model, Human Behavior, Social Networks, Emergency, Disaster Response, Nuclear Weapon of Mass Destruction.
References
Bagheri-Jebelli, N., Crooks, A.T. and Kennedy, W.G. (2019), Capturing the Effects of Gentrification on Property Values: An Agent-Based Modeling Approach, The 2019 Computational Social Science Society of Americas Conference, Santa Fe, NM. (pdf) Burger, A. G., Kennedy, W.G., Crooks, A.T., Jiang, N. and Guillen-Piazza, D. (2019), Modeling Social Networks in an Agent-Based Model of a Nuclear Weapon of Mass Destruction Event, The 2019 Computational Social Science Society of Americas Conference, Santa Fe, NM. (paper pdf) (poster pdf)
Do vaccine discussions on Twitter show a
highly clustered pattern in the sense that users tend to
communicate more often with those who have same opinions
towards vaccination than those who do not?
If the
communication is highly clustered, to what extent do pro-vaccine
users reach out to anti-vaccine users
and vice versa?
How much do social bots,
computer algorithms designed to mimic human behavior and
interact with humans in an automated fashion, contribute to
the conversation as previous research has shown that social
bots can have certain impact on human communication in
social media?
In order to answer these
questions, we use a variety of machine learning techniques (e.g. logistic regression, support vector machine (e.g. linear
and non-linear kernel), k-nearest neighbors, nearest centroid,
and Naïve Bayes) trained with labeled data (which is available at https://github.com/XiaoyiYuan/vaccination_online_discussion) to categorize each user’s
vaccination stance. By exploring a combination of opinion groups and retweet networks we discovered that pro- and anti-vaccine users retweet predominantly from their own opinion group, while users with neutral opinions are distributed across communities. In addition, our bot analysis (using the open-source DeBot detection platform) discovered that 1.45% of the corpus users were identified as likely bots and these produced 4.59% of all tweets within our data set. If you wish to find out more about our paper, below you can read the abstract along with seeing some figures including a sketch of our methodology, a selection of results and a link to the paper.
Abstract:
Many states in the United States allow a “belief exemption” for measles, mumps, and rubella (MMR) vaccines. People’s opinion on whether or not to take the vaccine can have direct consequences in public health. Social media has been one of the dominant communication channels for people to express their opinions of vaccination. Despite governmental organizations’ efforts of disseminating information of vaccination benefits, anti-vaccine sentiment is still gaining momentum. Studies have shown that bots on social media (i.e., social bots) can influence opinion trends by posting a substantial number of automated messages. The research presented here investigates the communication patterns of anti- and pro-vaccine users and the role of bots in Twitter by studying a retweet network related to MMR vaccine after the 2015 California Disneyland measles outbreak. We first classified the users into anti-vaccination, neutral to vaccination, and pro-vaccination groups using supervised machine learning. We discovered that pro- and anti-vaccine users retweet predominantly from their own opinion group. In addition, our bot analysis discovers that 1.45% of the corpus users were identified as likely bots which produced 4.59% of all tweets within our dataset. We further found that bots display hyper-social tendencies by initiating retweets at higher frequencies with users within the same opinion group. The article concludes that highly clustered anti-vaccine Twitter users make it difficult for health organizations to penetrate and counter opinionated information while social bots may be deepening this trend. We believe that these findings can be useful in developing strategies for health communication of vaccination.
Keywords: Anti-vaccine Movement, Twitter, Social Media, Opinion Classification, Bot Analysis
Full Reference:
Yuan, X., Schuchard, R. and Crooks, A.T. (2019), Examining Emergent Communities and Detecting Social Bots within the Polarized Online Vaccination Debate in Twitter, Social Media + Society. https://doi.org/10.1177/2056305119865465 (pdf)
For those who are not on the MASON list-serve, the other day Sean Luke posted a message regarding the a new release (MASON 20) which is part of our NSF CI-EN: Enhancement of a Large-scale Multiagent Simulation Tool project. In this new release (apart from bugfixes) there are some new features. The first is a new distributed parameter sweep package which enables you to run many simulations in parallel with different parameter settings (similar to BehaviorSpace in NetLogo). Next up is an update to GeoMASON, not only are there new demos (as shown below) but changes in the code to enable demos and other applications to be loaded from jar files. The third update is Distributed MASON, jointly developed with ISISLab at the University of Salerno (it's not D-MASON ). The objective of distributed MASON is to make it possible to port MASON applications to run in cloud computing architectures (more details and example models including distributed HeatBugs, Flockers, and CampusWorld can be seen in Wang et al., 2018). For more details check out the MASON webpage: http://cs.gmu.edu/~eclab/projects/mason/.
A selection of GeoMason Models included in the new release.
Publications relating to the project:
Wang, H., Wei, E., Simon, R., Luke, S., Crooks, A.T., Freelan, D.
and Spagnuolo, C. (2018), Scalability in the MASON multi-agent
simulation system, in Besada, E., Polo, Ó.R., De Grande, R. and Risco
J.L (eds.). Proceedings of the 22nd International Symposium on Distributed Simulation and Real Time Applications, Madrid, Spain, pp. 135-144. (pdf)
Luke, S., Simon, R., Crooks, A.T., Wang, H., Wei, E., Freelan,
D., Spagnuolo, C., Scarano, V., Cordasco, G. and Cioffi-Revilla, C.
(2018), The MASON Simulation Toolkit: Past, Present, and Future, in
Davidsson P. and Verhagen H. (eds.), Proceedings of the 19th International Workshop on Multi-Agent-Based Simulation, Stockholm, Sweden, pp. 75-87. (pdf)
At the recent SPIE Optics + Photonics Conference we had a paper entitled "The Impact of Message Quality on Entity Location and Identification Performance in Distributed Situational Awareness." In the paper we discuss the importance of detecting a person or object in complicated and dynamic environments (such as for search and rescue or law enforcement). However, with the growth in sensors and the resulting information from them, the identification and tracking of objects is becoming more difficult. As a result, in this paper we provide and assess a method to identify objects and the interactions between agents (human or technological) within a collaborative system for improving situational awareness. Below we provide the abstract to the paper, some images of the system along with some results and a link to the paper.
Abstract
Location and time are critical to the success of many organizations’ missions. Sensors, software, processors, vehicles, and human analysts work together to accomplish these tasks of detecting and identifying specific entities as quickly as possible for these missions. This work aims to make a contribution by providing a team-based detection and identification performance model incorporating the theory of Distributed Situational Awareness (DSA) and its effect on completing a specific task. The task being the ability to detect and identify a specific entity within a complex urban environment. Conditions to accomplish the task is the utilization of two unmanned aerial vehicles mounted with electro-optical sensors, operated by two analysts, creating a team to execute this task. Our results provide an additional resource on the how technology and training might be utilized to find the best performance given these certain conditions and missions. A highly trained team might improve their performance with this technology, or a team with low training could perform at a high level given the appropriate technology in limited time scenarios. More importantly, the model presented in this paper provides an evaluation tool to compare new technologies and their impact on teams. Specifically, it enables answering questions, such as: is an investment in new technology appropriate if investing in additional training produces the same performance results? Future performance can also be evaluated based on the team’s level of training and use of technology for these specific tasks.
Keywords: Situational Awareness, Identification, Detection, Sensors, Training, Team.
Snapshot from FOCUS depicting the flight paths of the unmanned aerial vehicles (UAVs) and sensor field of view in green.
LiDAR map of the city of Samarra, Iraq utilized in FOCUS for this experiment.
Identification of Situational Awareness (SA) level data sets - baseline. Histogram and distribution curve.
Full Reference:
Bates, C.T., Croitoru, A., Crooks, A.T. and Harclerode, E. (2019), The Impact of Message Quality on Entity Location and Identification Performance in Distributed Situational Awareness, Proceedings of the SPIE Optics + Photonics, San Diego, CA.
Paper 11137-64 (pdf)
