(Re)shaping online narratives: when bots promote the message of President Trump during his first impeachment.

Influencing and framing debates on Twitter provides power to shape public opinion. Bots have become essential tools of 'computational propaganda' on social media such as Twitter, often contributing to a large fraction of the tweets regarding political events such as elections. Although analyses have been conducted regarding the first impeachment of former president Donald Trump, they have been focused on either a manual examination of relatively few tweets to emphasize rhetoric, or the use of Natural Language Processing (NLP) of a much larger corpus with respect to common metrics such as sentiment. In this paper, we complement existing analyses by examining the role of bots in the first impeachment with respect to three questions as follows. (Q1) Are bots actively involved in the debate? (Q2) Do bots target one political affiliation more than another? (Q3) Which sources are used by bots to support their arguments? Our methods start with collecting over 13M tweets on six key dates, from October 6th 2019 to January 21st 2020. We used machine learning to evaluate the sentiment of the tweets (via BERT) and whether it originates from a bot. We then examined these sentiments with respect to a balanced sample of Democrats and Republicans directly relevant to the impeachment, such as House Speaker Nancy Pelosi, senator Mitch McConnell, and (then former Vice President) Joe Biden. The content of posts from bots was further analyzed with respect to the sources used (with bias ratings from AllSides and Ad Fontes) and themes. Our first finding is that bots have played a significant role in contributing to the overall negative tone of the debate (Q1). Bots were targeting Democrats more than Republicans (Q2), as evidenced both by a difference in ratio (bots had more negative-to-positive tweets on Democrats than Republicans) and in composition (use of derogatory nicknames). Finally, the sources provided by bots were almost twice as likely to be from the right than the left, with a noticeable use of hyper-partisan right and most extreme right sources (Q3). Bots were thus purposely used to promote a misleading version of events. Overall, this suggests an intentional use of bots as part of a strategy, thus providing further confirmation that computational propaganda is involved in defining political events in the United States. As any empirical analysis, our work has several limitations. For example, Trump's rhetoric on Twitter has previously been characterized by an overly negative tone, thus tweets detected as negative may be echoing his message rather than acting against him. Previous works show that this possibility is limited, and its existence would only strengthen our conclusions. As our analysis is based on NLP, we focus on processing a large volume of tweets rather than manually reading all of them, thus future studies may complement our approach by using qualitative methods to assess the specific arguments used by bots.

Analyzing the impact of social factors on homelessness: a fuzzy cognitive map approach.

BACKGROUND: The forces which affect homelessness are complex and often interactive in nature. Social forces such as addictions, family breakdown, and mental illness are compounded by structural forces such as lack of available low-cost housing, poor economic conditions, and insufficient mental health services. Together these factors impact levels of homelessness through their dynamic relations. Historic models, which are static in nature, have only been marginally successful in capturing these relationships. METHODS: Fuzzy Logic (FL) and fuzzy cognitive maps (FCMs) are particularly suited to the modeling of complex social problems, such as homelessness, due to their inherent ability to model intricate, interactive systems often described in vague conceptual terms and then organize them into a specific, concrete form (i.e., the FCM) which can be readily understood by social scientists and others. Using FL we converted information, taken from recently published, peer reviewed articles, for a select group of factors related to homelessness and then calculated the strength of influence (weights) for pairs of factors. We then used these weighted relationships in a FCM to test the effects of increasing or decreasing individual or groups of factors. Results of these trials were explainable according to current empirical knowledge related to homelessness. RESULTS: Prior graphic maps of homelessness have been of limited use due to the dynamic nature of the concepts related to homelessness. The FCM technique captures greater degrees of dynamism and complexity than static models, allowing relevant concepts to be manipulated and interacted. This, in turn, allows for a much more realistic picture of homelessness. Through network analysis of the FCM we determined that Education exerts the greatest force in the model and hence impacts the dynamism and complexity of a social problem such as homelessness. CONCLUSIONS: The FCM built to model the complex social system of homelessness reasonably represented reality for the sample scenarios created. This confirmed that the model worked and that a search of peer reviewed, academic literature is a reasonable foundation upon which to build the model. Further, it was determined that the direction and strengths of relationships between concepts included in this map are a reasonable approximation of their action in reality. However, dynamic models are not without their limitations and must be acknowledged as inherently exploratory.

Social interactions of eating behaviour among high school students: a cellular automata approach.

BACKGROUND: Overweight and obesity in children and adolescents is a global epidemic posing problems for both developed and developing nations. The prevalence is particularly alarming in developed nations, such as the United States, where approximately one in three school-aged adolescents (ages 12-19) are overweight or obese. Evidence suggests that weight gain in school-aged adolescents is related to energy imbalance exacerbated by the negative aspects of the school food environment, such as presence of unhealthy food choices. While a well-established connection exists between the food environment, presently there is a lack of studies investigating the impact of the social environment and associated interactions of school-age adolescents. This paper uses a mathematical modelling approach to explore how social interactions among high school adolescents can affect their eating behaviour and food choice. METHODS: In this paper we use a Cellular Automata (CA) modelling approach to explore how social interactions among school-age adolescents can affect eating behaviour, and food choice. Our CA model integrates social influences and transition rules to simulate the way individuals would interact in a social community (e.g., school cafeteria). To replicate these social interactions, we chose the Moore neighbourhood which allows all neighbours (eights cells in a two-dimensional square lattice) to influence the central cell. Our assumption is that individuals belong to any of four states; Bring Healthy, Bring Unhealthy, Purchase Healthy, and Purchase Unhealthy, and will influence each other according to parameter settings and transition rules. Simulations were run to explore how the different states interact under varying parameter settings. RESULTS: This study, through simulations, illustrates that students will change their eating behaviour from unhealthy to healthy as a result of positive social and environmental influences. In general, there is one common characteristic of changes across time; students with similar eating behaviours tend to form groups, represented by distinct clusters. Transition of healthy and unhealthy eating behaviour is non-linear and a sharp change is observed around a critical point where positive and negative influences are equal. CONCLUSIONS: Conceptualizing the social environment of individuals is a crucial step to increasing our understanding of obesogenic environments of high-school students, and moreover, the general population. Incorporating both contextual, and individual determinants found in real datasets, in our model will greatly enhance calibration of future models. Complex mathematical modelling has a potential to contribute to the way public health data is collected and analyzed.

Supporting meningitis diagnosis amongst infants and children through the use of fuzzy cognitive mapping.

BACKGROUND: Meningitis is characterized by an inflammation of the meninges, or the membranes surrounding the brain and spinal cord. Early diagnosis and treatment is crucial for a positive outcome, yet identifying meningitis is a complex process involving an array of signs and symptoms and multiple causal factors which require novel solutions to support clinical decision-making. In this work, we explore the potential of fuzzy cognitive map to assist in the modeling of meningitis, as a support tool for physicians in the accurate diagnosis and treatment of the condition. METHODS: Fuzzy cognitive mapping (FCM) is a method for analysing and depicting human perception of a given system. FCM facilitates the development of a conceptual model which is not limited by exact values and measurements and thus is well suited to representing relatively unstructured knowledge and associations expressed in imprecise terms. A team of doctors (physicians), comprising four paediatricians, was formed to define the multifarious signs and symptoms associated with meningitis and to identify risk factors integral to its causality, as indicators used by clinicians to identify the presence or absence of meningitis in patients. The FCM model, consisting of 20 concept nodes, has been designed by the team of paediatricians in collaborative dialogue with the research team. RESULTS: The paediatricians were supplied with a form containing various input parameters to be completed at the time of diagnosing meningitis among infants and children. The paediatricians provided information on a total of 56 patient cases amongst children whose age ranged from 2 months to 7 years. The physicians' decision to diagnose meningitis was available for each individual case which was used as the outcome measure for evaluating the model. The FCM was trained using 40 cases with an accuracy of 95%, and later 16 test cases were used to analyze the accuracy and reliability of the model. The system produced the results with sensitivity of 83.3% and specificity of 80%. CONCLUSIONS: This work suggests that the application and development of a knowledge based system, using the formalization of FCMs for understanding the symptoms and causes of meningitis in children and infants, can provide a reliable front-end decision-making tool to better assist physicians.