Wednesday, September 04, 2019

Communities, Bots and Vaccinations

Following on from our work on bots and health discussions in relation to online social networks (OSNs), Xiaoyi Yuan, Ross Schuchard and myself have just published a paper entitled "Examining Emergent Communities and Detecting Social Bots within the Polarized Online Vaccination Debate in Twitter" in Social Media + Society. Within the paper we explore the communication patterns of vaccine discussions in Twitter. More specifically we ask three questions:
  1. 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? 
  2. If the communication is highly clustered, to what extent do pro-vaccine users reach out to anti-vaccine users and vice versa? 
  3. 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)

Tuesday, September 03, 2019

Updates to the MASON

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

Friday, August 30, 2019

Message Quality on Entity Location and Identification Performance

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)

Monday, August 26, 2019

Call for Papers: Humans, Societies and Artificial Agents - SpringSim


At the upcoming 2020 Spring Simulation (SpringSim) Conference being held at George Mason University, Philippe Giabbanelli and myslef are organizing a tract entitled Humans, Societies and Artificial Agents. 

Aims and Scope:

In the Humans, Societies and Artificial Agents (HSAA) Track, you will see that artificial societies have typically relied on agent-based models, Geographical Information Systems (GIS), or cellular automata to capture the decision-making processes of individuals in relation to places and/or social interactions. This has supported a wide range of applications (e.g., in archaeology, economics, geography, psychology, political science, or health) and research tasks (e.g., what-if scenarios or predictive models, models to guide data collection). Several opportunities have recently emerged that augment the capacity of artificial societies at capturing complex human and social behavior. Mixed-methods and hybrid approaches now enable the use of ‘big data’, for instance by combining machine learning with artificial societies to explore the model’s output (i.e., artificial societies as input to machine learning), define the model structure (i.e. machine learning as a preliminary to designing artificial societies), or run a model efficiently (i.e. machine learning as a proxy or surrogate to artificial societies). Datasets are also broader in type since artificial societies can now be built from text, or generate textual as well as visual outputs to better engage end-users. Authors are encouraged to submit papers in the following areas:
  • Artificial agents and societies (e.g., case studies, analyses of moral and ethical considerations)
  • Participatory modeling and simulation
  • Policy development and evaluation through simulations
  • Predictive models of social behavior
  • Simulations of societies as public educational tools
  • Mixed-methods (e.g., analyzing or generating text data with artificial societies, combining machine learning and artificial societies)
  • Models of individual decision-making, mobility patterns, or socio-environmental interactions
  • Testbeds and environments to facilitate artificial society development
  • Tools and methods (e.g., agent-based models, case-based modeling, soft systems)

Important Dates
  • Paper Submission: December 16, 2019 
  • Author Notification: February 17, 2020 
  • Camera-Ready: March 4, 202

For more information, including submission guidelines can be found at https://scs.org/springsim/.  

Thursday, August 01, 2019

Bot stamina: Examining the influence and staying power of bots in online social networks

Following on with our work on bots we just had a paper published in Applied Network Science entitled "Bot Stamina: Examining the Influence and Staying Power of Bots in Online Social Networks" which is significant extension of a previous conference paper. In the paper we look at thee global Twitter conversions in 2016. Specifically the 2016 U.S. presidential election primary races (February 1–28, 2016), the ongoing Ukrainian conflict (August 1–28, 2016), and the Turkish government’s implementation of censorship (December 1–28, 2016) and the influence of Bots on these conversations.

Tweets were classified as Bots using DeBot and then we explore the relative importance and persistence of social bots in online social networks by looking at retweet networks and centrality rankings (i.e. degree, in-degree, out-degree, eigenvector, betweenness and PageRank). We find through such centrality measurements that even though Bots made up less than 0.3% of the total user population, they displayed a profound level of structural network influence.  If you would like to know more about this work, below we provide the abstract to the paper, along with some figures, including one that describes our methodology, and some initial results. Finally at the bottom of the page we provide the full reference and a link to the paper.

Abstract
This study presents a novel approach to expand the emergent area of social bot research. We employ a methodological framework that aggregates and fuses data from multiple global Twitter conversations with available bot detection platforms and ultimately classifies the relative importance and persistence of social bots in online social networks (OSNs). In testing this methodology across three major global event OSN conversations in 2016, we confirmed the hyper-social nature of bots: suspected social bot accounts make far more attempts on average than social media accounts attributed to human users to initiate contact with other accounts via re-tweets. Social network analysis centrality measurements discover that social bots, while comprising less than 0.3% of the total corpus user population, display a dis-proportionately high profound level of structural network influence by ranking particularly high among the top users across multiple centrality measures within the OSN conversations of interest. Further, we show that social bots exhibit temporal persistence in centrality ranking density when examining these same OSN conversations over time.

Keywords: Social bot analysis, computational social science, social network analysis, online social networks




Full Reference:
Schuchard, R., Crooks, A.T., Stefanidis, A. and Croitoru, A. (2019), Bot Stamina: Examining the Influence and Staying Power of Bots in Online Social Networks, Applied Network Science, 4: 55. Available at https://doi.org/10.1007/s41109-019-0164-x. (pdf)