arXiv subjects

Ivan Garibay

Publications and source records attributed to Ivan Garibay.

48 records · Page 3Linked to original sources

arXiv2020

Resistance of communities against disinformation

The spread of disinformation is considered a big threat to societies and has recently received unprecedented attention. In this paper we propose an agent-based model to simulate dissemination of a conspiracy in a population. The model is able to compare the resistance of different network structures against the activity of conspirators. Results show that connectedness of network structure and centrality of conspirators are of crucial importance in preventing conspiracies from becoming widespread.

cs.SI↗

arXiv2020

The Degree-Dependent Threshold Model: Towards a Better Understanding of Opinion Dynamics on Online Social Networks

With the rapid growth of online social media, people become increasingly overwhelmed by the volume and the content of the information present in the environment. The threshold model is currently one of the most common methods to capture the effect of people on others' opinions and emotions. Although many studies employ and try to improve upon the threshold model, the search for an appropriate threshold function for defining human behavior is an essential and yet unattained quest. The definition of heterogeneity in thresholds of individuals is oftentimes poorly defined, which leads to the rather simplistic use of uniform and binary functions, albeit they are far from representing the reality. In this study, we use Twitter data of size 30,704,025 tweets to mimic the adoption of a new opinion. Our results show that the threshold is not only correlated with the out-degree of nodes, which contradicts other studies but also correlated with nodes' in-degree. Therefore, we simulated two cases in which thresholds are out-degree and in-degree dependent, separately. We concluded that the system is more likely to reach a consensus when thresholds are in-degree dependent; however, the time elapsed until all nodes fix their opinions is significantly higher in this case. Additionally, we did not observe a notable effect of mean-degree on either the average opinion or the fixation time of opinions for both cases, and increasing seed size has a negative effect on reaching a consensus. Although threshold heterogeneity has a slight influence on the average opinion, the positive effect of heterogeneity on reaching a consensus is more pronounced when thresholds are in-degree dependent.

cs.SI↗

arXiv2020

The Effects of Information Overload on Online Conversation Dynamics

The inhibiting effects of information overload on the behavior of online social media users, can affect the population-level characteristics of information dissemination through online conversations. We introduce a mechanistic, agent-based model of information overload and investigate the effects of information overload threshold and rate of information loss on observed online phenomena. We find that conversation volume and participation are lowest under high information overload thresholds and mid-range rates of information loss. Calibrating the model to user responsiveness data on Twitter, we replicate and explain several observed phenomena: 1) Responsiveness is sensitive to information overload threshold at high rates of information loss; 2) Information overload threshold and rate of information loss are Pareto-optimal and users may experience overload at inflows exceeding 30 notifications per hour; 3) Local abundance of small cascades of modest global popularity and local scarcity of larger cascades of high global popularity explains why overloaded users receive, but do not respond to large, highly popular cascades; 4) Users typically work with 7 notifications per hour; 5) Over-exposure to information can suppress the likelihood of response by overloading users, contrary to analogies to biologically-inspired viral spread. Reconceptualizing information spread with the mechanisms of information overload creates a richer representation of online conversation dynamics, enabling a deeper understanding of how (dis)information is transmitted over social media.

cs.SI↗

arXiv2019

A Comprehensive Survey on Machine Learning Techniques and User Authentication Approaches for Credit Card Fraud Detection

With the increase of credit card usage, the volume of credit card misuse also has significantly increased. As a result, financial organizations are working hard on developing and deploying credit card fraud detection methods, in order to adapt to ever-evolving, increasingly sophisticated defrauding strategies and identifying illicit transactions as quickly as possible to protect themselves and their customers. Compounding on the complex nature of such adverse strategies, credit card fraudulent activities are rare events compared to the number of legitimate transactions. Hence, the challenge to develop fraud detection that are accurate and efficient is substantially intensified and, as a consequence, credit card fraud detection has lately become a very active area of research. In this work, we provide a survey of current techniques most relevant to the problem of credit card fraud detection. We carry out our survey in two main parts. In the first part,we focus on studies utilizing classical machine learning models, which mostly employ traditional transnational features to make fraud predictions. These models typically rely on some static physical characteristics, such as what the user knows (knowledge-based method), or what he/she has access to (object-based method). In the second part of our survey, we review more advanced techniques of user authentication, which use behavioral biometrics to identify an individual based on his/her unique behavior while he/she is interacting with his/her electronic devices. These approaches rely on how people behave (instead of what they do), which cannot be easily forged. By providing an overview of current approaches and the results reported in the literature, this survey aims to drive the future research agenda for the community in order to develop more accurate, reliable and scalable models of credit card fraud detection.

cs.LG↗

arXiv2019

Supervised Machine Learning based Ensemble Model for Accurate Prediction of Type 2 Diabetes

According to the American Diabetes Association(ADA), 30.3 million people in the United States have diabetes, but only 7.2 million may be undiagnosed and unaware of their condition. Type 2 diabetes is usually diagnosed for most patients later on in life whereas the less common Type 1 diabetes is diagnosed early on in life. People can live healthy and happy lives while living with diabetes, but early detection produces a better overall outcome on most patient's health. Thus, to test the accurate prediction of Type 2 diabetes, we use the patients' information from an electronic health records company called Practice Fusion, which has about 10,000 patient records from 2009 to 2012. This data contains individual key biometrics, including age, diastolic and systolic blood pressure, gender, height, and weight. We use this data on popular machine learning algorithms and for each algorithm, we evaluate the performance of every model based on their classification accuracy, precision, sensitivity, specificity/recall, negative predictive value, and F1 score. In our study, we find that all algorithms other than Naive Bayes suffered from very low precision. Hence, we take a step further and incorporate all the algorithms into a weighted average or soft voting ensemble model where each algorithm will count towards a majority vote towards the decision outcome of whether a patient has diabetes or not. The accuracy of the Ensemble model on Practice Fusion is 85\%, by far our ensemble approach is new in this space. We firmly believe that the weighted average ensemble model not only performed well in overall metrics but also helped to recover wrong predictions and aid in accurate prediction of Type 2 diabetes. Our accurate novel model can be used as an alert for the patients to seek medical evaluation in time.

cs.LG↗

arXiv2019

Forecasting the Success of Television Series using Machine Learning

Television is an ever-evolving multi billion dollar industry. The success of a television show in an increasingly technological society is a vast multi-variable formula. The art of success is not just something that happens, but is studied, replicated, and applied. Hollywood can be unpredictable regarding success, as many movies and sitcoms that are hyped up and promise to be a hit end up being box office failures and complete disappointments. In current studies, linguistic exploration is being performed on the relationship between Television series and target community of viewers. Having a decision support system that can display sound and predictable results would be needed to build confidence in the investment of a new TV series. The models presented in this study use data to study and determine what makes a sitcom successful. In this paper, we use descriptive and predictive modeling techniques to assess the continuing success of television comedies: The Office, Big Bang Theory, Arrested Development, Scrubs, and South Park. The factors that are tested for statistical significance on episode ratings are character presence, director, and writer. These statistics show that while characters are indeed crucial to the shows themselves, the creation and direction of the shows pose implication upon the ratings and therefore the success of the shows. We use machine learning based forecasting models to accurately predict the success of shows. The models represent a baseline to understanding the success of a television show and how producers can increase the success of current television shows or utilize this data in the creation of future shows. Due to the many factors that go into a series, the empirical analysis in this work shows that there is no one-fits-all model to forecast the rating or success of a television show.

cs.LG↗

arXiv2019

DeepFork: Supervised Prediction of Information Diffusion in GitHub

Information spreads on complex social networks extremely fast, in other words, a piece of information can go viral within no time. Often it is hard to barricade this diffusion prior to the significant occurrence of chaos, be it a social media or an online coding platform. GitHub is one such trending online focal point for any business to reach their potential contributors and customers, simultaneously. By exploiting such software development paradigm, millions of free software emerged lately in diverse communities. To understand human influence, information spread and evolution of transmitted information among assorted users in GitHub, we developed a deep neural network model: DeepFork, a supervised machine learning based approach that aims to predict information diffusion in complex social networks; considering node as well as topological features. In our empirical studies, we observed that information diffusion can be detected by link prediction using supervised learning. DeepFork outperforms other machine learning models as it better learns the discriminative patterns from the input features. DeepFork aids in understanding information spread and evolution through a bipartite network of users and repositories i.e., information flow from a user to repository to user.

cs.SI↗

arXiv2019

Evolutionary model discovery of causal factors behind the socio-agricultural behavior of the ancestral Pueblo

Agent-based modeling of artificial societies offers a platform to test human-interpretable, causal explanations of human behavior that generate society-scale phenomena. However, parameter calibration is insufficient to conduct an adequate data-driven exploration of the importance of causal factors that constitute agent rules, resulting in models with limited causal accuracy and robustness. We introduce evolutionary model discovery, a framework that combines genetic programming and random forest regression to evaluate the importance of a set of causal factors hypothesized to affect the individual's decision-making process. We investigated the farm plot seeking behavior of the ancestral Pueblo of the Long House Valley simulated in the Artificial Anasazi model our proposed framework. We evaluated the importance of causal factors not considered in the original model that we hypothesized to have affected the decision-making process. Contrary to the original model, where closeness was the sole factor driving farm plot selection, selection of higher quality land and desire for social presence are shown to be more important. In fact, model performance is improved when agents select farm plots further away from their failed farm plot. Farm selection strategies designed using these insights into the socio-agricultural behavior of the ancestral Pueblo significantly improved the model's accuracy and robustness.

cs.MA↗

arXiv2019

A Cross-Repository Model for Predicting Popularity in GitHub

Social coding platforms, such as GitHub, can serve as natural laboratories for studying the diffusion of innovation through tracking the pattern of code adoption by programmers. This paper focuses on the problem of predicting the popularity of software repositories over time; our aim is to forecast the time series of popularity-related events (code forks and watches). In particular, we are interested in cross-repository patterns-how do events on one repository affect other repositories? Our proposed LSTM (Long Short-Term Memory) recurrent neural network integrates events across multiple active repositories, outperforming a standard ARIMA (Auto-Regressive Integrated Moving Average) time series prediction based on the single repository. The ability of the LSTM to leverage cross-repository information gives it a significant edge over standard time series forecasting.

cs.SI↗

arXiv2018

How polarization can provide an increase in content dissemination amongst the highly ranked influencers

This work extends a model of simulating influence in a network of stochastic edge dynamics to account for polarization. The model built upon is termed Dynamic Communicators and seeks to understand the process which produces low volume, high influence amongst users. This model is extended to introduce the effects polarization. The fundamental assumption of the model is that a parameter of importance governs the rate of message responsiveness. With the introduction of relative incremental changes according to the response incurred in adjacent nodes receiving content, the changes in the power brokerage of a network can be examined. This provides a content agnostic interpretation for the desire to proliferate content amongst peers. From the results of the simulations, the analysis shows that a lack of polarization incrementally develops a more level discussion network with more even response rates whereas the polarization introduction leads to a gradual increase in response rate disparity.

cs.SI↗

arXiv2016

Evaluation of Zika Vector Control Strategies Using Agent-Based Modeling

Aedes Aegypti is the vector of several deadly diseases, including Zika. Effective and sustainable vector control measures must be deployed to keep A. aegypti numbers under control. The distribution of A. Aegypti is subject to spatial and climatic constraints. Using agent-based modeling, we model the population dynamics of A. aegypti subjected to the spatial and climatic constraints of a neighborhood in the Key West. Satellite imagery was used to identify vegetation, houses (CO2 zones) both critical to the mosquito lifecycle. The model replicates the seasonal fluctuation of adult population sampled through field studies and approximates the population at a high of 986 (95% CI: [979, 993]) females and 1031 (95% CI: [1024, 1039]) males in the fall and a low of 316 (95% CI: [313, 319]) females and 333 (95% CI: [330, 336]) males during the winter. We then simulate two biological vector control strategies: 1) Wolbachia infection and 2) Release of Insects carrying a Dominant Lethal gene (RIDL). Our results support the probability of sustained Wolbachia infection within the population for two years after the year of release. egies, our approach provides a realistic simulation environment consisting of male and female Aedes aegypti, breeding spots, vegetation and CO2 sources.

q-bio.PE↗

arXiv2011

Transformation Networks: How Innovation and the Availability of Technology can Increase Economic Performance

A transformation network describes how one set of resources can be transformed into another via technological processes. Transformation networks in economics are useful because they can highlight areas for future innovations, both in terms of new products, new production techniques, or better efficiency. They also make it easy to detect areas where an economy might be fragile. In this paper, we use computational simulations to investigate how the density of a transformation network affects the economic performance, as measured by the gross domestic product (GDP), of an artificial economy. Our results show that on average, the GDP of our economy increases as the density of the transformation network increases. We also find that while the average performance increases, the maximum possible performance decreases and the minimum possible performance increases.

cs.SI↗