William Rand

University of Maryland, College Park | UMD, UMCP, University of Maryland College Park · Marketing, Information Systems and Computer Science

Herding behavior has a social cost for individuals not following the herd, influencing human decision-making. This work proposes including a social cost derived from herding mentality into the payoffs of pairwise game interactions. We introduce a co-evolutionary asymmetric model with four individual strategies (cooperation vs. defection and herding...

Agent-based modeling has proven to be a useful simulation tool in marketing to analyze what-if scenarios and support strategic marketing decisions. Over the years, the field has evolved and there is a substantial number of scientific publications that focus on different aspects of agent-based modeling. However, there is no recent bibliometric analy...

Diffusion of information through complex networks is of interest in studies such as propagation prediction and influence maximization, both of which have applications in viral marketing and rumor controlling. There are a variety of information diffusion models, all of which simulate the adoption and spread of information over time. However, there i...

Online disinformation actors are those individuals or bots who disseminate false or misleading information over social media, with the intent to sway public opinion in the information domain towards harmful social outcomes. Quantification of the degree to which users post or respond intentionally versus under social influence, remains a challenge,...

Social media platforms are becoming increasingly important marketing channels, and recently these channels are becoming dominated by content that is not textual, but visual in nature. In this paper, we explore the relationship between the visual complexity of firm-generated imagery (FGI) and consumer liking on social media. We use previously valida...

This paper explains the design of a social network analysis framework, developed under DARPA’s SocialSim program, with novel architecture that models human emotional, cognitive, and social factors. Our framework is both theory and data-driven, and utilizes domain expertise. Our simulation effort helps understanding how information flows and evolves...

Communication networks are known to exhibit asymmetric influence structures, constructed of a spectrum from highly influential individuals to highly influenced individuals. Information Processing Capacity (IPC) determines the level of responsiveness expressed by individuals when communicating with others in such networks. In this study, we explore...

Market diffusion of new products is driven by the actions and reactions of consumers, distributors, competitors, and other stakeholders, all of whom can be heterogeneous in their individual characteristics, attitudes, needs, and objectives. These actors may also interact with others in various ways (e.g., through word of mouth or social influence)....

Influence cascades are typically analyzed using a single metric approach, i.e., all influence is measured using one number. However, social influence is not monolithic; different users exercise different influences in different ways, and influence is correlated with the user and content-specific attributes. One such attribute could be whether the a...

Human decision-making is subject to the biological limits of cognition. The fluidity of information propagation over online social media often leads users to experience information overload. This in turn affects which information received by users are processed and gain a response to, imposing constraints on volumes of, and participation in, inform...

Communication networks are known to exhibit asymmetric influence structures, constructed of a spectrum from highly influential individuals to highly influenced individuals. Information Processing Capacity (IPC) determines the level of responsiveness expressed by individuals when communicating with others in such networks. In this study we explore t...

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 inform...

This paper explains the design of a social network analysis framework, developed under DARPA's SocialSim program, with novel architecture that models human emotional, cognitive and social factors. Our framework is both theory and data-driven, and utilizes domain expertise. Our simulation effort helps in understanding how information flows and evolv...

Artificial intelligence (AI) has proven to be useful in many applications from automating cars to providing customer service responses. However, though many firms want to take advantage of AI to improve marketing, they lack a process by which to execute a Marketing AI project. This article discusses the use of AI to provide support for marketing de...

Jury deliberations provide a quintessential example of collective decision-making, but few studies have probed the available data to explore how juries reach verdicts. We examine how features of jury dynamics can be better understood from the joint distribution of final votes and deliberation time. To do this, we fit several different decision-maki...

Contributors offered suggestions to improve multi‐scale modeling that focused mainly on getting model substance right. This chapter is an edited but not iterated recounting of responses to questions that deal with simulation and emergence, how to relate models at different levels of resolution, and how to assure more humanness in agents. Contributo...

With the growth of big data, there has been a rush to develop models in the social sciences that extract patterns of behavior from data without a corresponding theory to explain those behaviors. While it is useful to identify and examine these patterns, the use of these regularities for predictions and intervention is dangerous without theory. In t...

With the increasing abundance of 'digital footprints' left by human interactions in online environments, e.g., social media and app use, the ability to model complex human behavior has become increasingly possible. Many approaches have been proposed, however, most previous model frameworks are fairly restrictive. We introduce a new social modeling...

With the increasing abundance of “digital footprints” left by human interactions in online environments, e.g., social media and app use, the ability to model complex human behavior has become increasingly possible. Many approaches have been proposed, however, most previous model frameworks are fairly restrictive. We introduce a new social modeling...

Complex systems approaches are emerging as new methods that complement conventional analytical and statistical approaches for analyzing marketing phenomena. These methods can provide researchers with tools to understand and predict marketing outcomes that emerge at the aggregate level by modeling feedback between heterogeneous agents and agent inte...

Today's consumers are immersed in a vast and complex array of networks. Each network features an interconnected mesh of people and firms, and now, with the rise of the Internet of Things (IoT), also objects. Technology (particularly mobile devices) enables such connections, and facilitates many kinds of interactions in these networks—from transacti...

We explore how the mechanics of collective decision-making, especially of jury deliberation, can be inferred from macroscopic statistics. We first hypothesize that the dynamics of competing opinions can leave a "fingerprint" in the joint distribution of final votes and time to reach a decision. We probe this hypothesis by modeling jury datasets fro...

Marketers must constantly decide how to implement word-of-mouth (WOM) programs, and a well-developed decision support system (DSS) can provide them valuable assistance in doing so. The authors propose an agent-based framework that aggregates social network-level individual interactions to guide the construction of a successful DSS for WOM. The fram...

Social media provides a powerful platform for influencers to broadcast content to a large audience of followers. In order to reach the greatest number of users, an important first step is to identify times when a large portion of a target population is active on social media, which requires modeling the behavior of those individuals. We propose thr...

Crowds can often make better decisions than individuals or small groups of experts by leveraging their ability to aggregate diverse information. Question answering sites, such as Stack Exchange, rely on the “wisdom of crowds” effect to identify the best answers to questions asked by users. We analyze data from 250 communities on the Stack Exchange...

Changing the penalized regression method does not qualitatively change our findings. Ridge regression coefficients for voting on an (eventually) accepted answer before (red triangles) and after (blue squares) that answer is accepted, as well as accepting an answer (green circles) for (left column) technical, (central column) non-technical, and (rig...

Removing the largest board from our fits does not qualitatively change our findings. LASSO regression coefficients for voting on an (eventually) accepted answer before (triangles) and after (squares) that answer is accepted, as well as accepting an answer (circles) for (left column) technical, (central column) non-technical, and (right column) meta...

CDF normalization is especially resiliant to data noise. The standard deviation divided by the mean of best fit coefficients of simulated data (a measure of the relative variance of parameter estimates), where values are 1 with probability 11+exp(-(ax+by)) and 0 otherwise, and x and y are independent variables. In these simulations, x is normally d...

AUC versus number of answers for the full model, position null model, and social influence null model for non-technical and meta boards. AUC for (a) voting before an answer is accepted, (b) accepting an answer, and (c) voting after an answer is accepted versus the number of answers in non-technical boards, and (d-f) equivalent plots for meta boards...

Freemium apps are creating new marketing scenarios, encouraging product adoption through customer-to-customer interaction. Agent-based models have become a useful tool for helping marketers to understand social dynamics in freemium apps. However, the parameters of these models need to be calibrated using real data in order to adjust its behaviour t...

Marketers have to make decisions on how to implement word-of-mouth (WOM) programs and a well-developed decision support system (DSS) can provide them with valuable assistance. The authors propose an agent-based framework that aggregates social network-level individual interactions to guide the construction of a successful DSS for WOM. The framework...

The rapid diffusion of information is critical to combat the extreme levels of uncertainty and complexity that surround disaster relief operations. As a means of gathering and sharing information, humanitarian organizations are becoming increasingly reliant on social media platforms based on the Internet. In this paper, we present a field study tha...

Purpose The purpose of this commentary is to explain that it is not useful to unnecessarily complicate a model. Striving for realism for its own sake does not advance understanding; however, making sure that a model provides valid insights is a useful goal. Design/methodology/approach The authors advocate that a standard should exist based on whet...

Despite being freely accessible, open online community data can be difficult to use effectively. To access and analyze large amounts of data, researchers must become familiar with the meaning of data values. Then they must also find a way to obtain and process the datasets to extract their desired vectors of behavior and content. This process is fr...

Social media sites have created a reverberating "echoverse" for brand communication, forming complex feedback loops ("echoes") between the "universe" of corporate communications, news media, and user-generated social media. To understand these feedback loops, the authors process longitudinal, unstructured data using computational linguistics techni...

Crowds can often make better decisions than individuals or small groups of experts by leveraging their ability to aggregate diverse information. Question answering sites, such as Stack Exchange, rely on the "wisdom of crowds" effect to identify the best answers to questions asked by users. We analyze data from 250 communities on the Stack Exchange...

Crowds can often make better decisions than individuals or small groups of experts by leveraging their ability to aggregate diverse information. Question answering sites, such as Stack Exchange, rely on the "wisdom of crowds" effect to identify the best answers to questions asked by users. We analyze data from 250 communities on the Stack Exchange...

Previous research has recognized the significance of a team's work capacity and suggested the selection of team members based on individual skills and performance in alignment with task characteristics. However, work teams are complex systems with interdependence between workers and the social environment, and exhibit surprising, nonlinear behavior...

Social media provides a powerful platform for influencers to broadcast content to a large audience of followers. In order to reach the greatest number of users, an important first step is to identify times when a large portion of a target population is active on social media, which requires modeling the behavior of those individuals. We propose thr...

Complex Systems can be defined in a broad manner and embrace concepts from different fields of science, from physics to biology, to computing and social sci-ences. Mainly, the definition includes nonlinear dynamical systems that contain large number of interactions among the parts. These systems learn, evolve, and adapt, generating emergent non-det...

Sistemas complexos podem ser definidos de forma ampla e abraçar conceitos de diferentes campos da ciência, da física à biologia, à computação e às ciências sociais. O conceito central de sistemas complexos pressupõe sistemas dinâmicos, não lineares, que contêm grande número de interações entre as partes. Esses sistemas se modificam, de modo a apren...

Question and answer (Q&A) web sites have become increasing popular in recent years. These communities are social media platforms that enable users around the world to easily share their knowledge with each other. Q&A sites are based in part on the wisdom of crowds, i.e., everyone involved in the community can contribute something, and through colla...

We introduce a general contagion-like model for competing opinions that includes dynamic resistance to alternative opinions. We show that this model can describe candidate vote distributions, spatial vote correlations, and a slow approach to opinion consensus with sensible parameter values. These empirical properties of large groups, previously und...

Feature-rich social media can reveal many facets of individual user behavior; yet it is difficult to model such behavior due to both the noise and the overwhelming volume and heterogeneity in the data. In this paper, we address these challenges by building a model of user behavior in social media to understand the impact of users' actions on key in...

Social media is generated both in space and time, and in the context of disaster situations it can provide minute-by-minute and location-by-location awareness of the event and users’ concerns and feelings about crises. In this paper, we investigate the relationship between social media data, web donations, and traditional media coverage. We start b...

There has been substantial work exploring strategies, both theoretical and empirical, for selling and buying in online auctions. However, much of this work has considered single auctions in isolation, partially because it is hard to examine multiple simultaneous auctions using traditional math modeling approaches. In reality, many auctions occur si...

Although the role of social networks and consumer interactions in new product diffusion is widely acknowledged, such networks and interactions are often unobservable to researchers. What may be observable, instead, are aggregate diffusion patterns for past products adopted within a particular social network. The authors propose an approach for iden...

In this study we re-visit the pure versus hybrid strategy debate. Pure strategy advocates argue that competitive advantage is a direct function of efficiency and focus. Hybrid strategy advocates, in contrast, emphasize the importance of adaptability and flexibility for achieving advantage. The empirical evidence for the superiority of either strate...

As the volume of social media communications grow, many different stakeholders have sought to apply tools and methods for automatic identification of sentiment and topic in social network communications. In the domain of social media marketing it would be useful to automatically classify social media messaging into the classic framework of informat...

Recent work has attempted to capture the behavior of users on social media by modeling them as computational units processing information. We propose to extend this perspective by explicitly examining the predictive power of such a view. We consider a network of fifteen thousand users on Twitter over a seven week period. To evaluate the predictabil...

There is a large amount of interest in understanding users of social media in order to predict their behavior in this space. Despite this interest, user predictability in social media is not well-understood. To examine this question, we consider a network of fifteen thousand users on Twitter over a seven week period. We apply two contrasting modeli...

Spectrum policy debates are generally divided between advocates for more robust property rights that would allow Coasian bargaining and advocates for spectrum commons that would permit more unlicensed applications. As recent debates about the upcoming broadcast spectrum incentive auctions indicate, there is also basic disagreement about what the Fe...

Discovering automatically what people are talking about on social media with respect to a particular topic would be useful since it would give insight into how people perceive different topics. However, identifying trending terms/words within a topical conversation is a difficult task. We take an information retrieval approach and use tf-idf to ide...

In order to study the use of Twitter, it would be useful to be able to easily classify large volumes of messaging being used by Twitter users besides just in the traditional dimensions of positive and negative sentiment. For instance, in the space of social media marketing, it would be useful to be able to automatically identify social media messag...

During a crisis, understanding the diffusion of information throughout a population will provide insights into how quickly the population will react to the information, which can help those who need to respond to the event. The advent of social media has resulted in this information spreading quicker then ever before, and in qualitatively different...

There is a large amount of interest in understanding users of social media in order to predict their behavior in this space. Despite this interest, user predictability in social media is not well-understood. To examine this question, we consider a network of fifteen thousand users on Twitter over a seven week period. We apply two contrasting modeli...

Agent-based models can be manipulated to replicate real- world datasets, but choosing the best set of parameters to achieve this result can be difficult. To validate a model, the real-world dataset is often divided into a training and test set. The training set is used to calibrate the parameters and the test set is used to determine if the calibra...

We present a microblog recommendation system that can help monitor users, track conversations, and potentially improve diffusion impact. Given a Twitter network of active users and their followers, and historical activity of tweets, retweets and mentions, we build upon a prediction tool to predict the Top K users who will retweet or mention a focal...

We present a recommendation system for social media that draws upon monitoring and prediction methods. We use historical posts on some focal topic or historical links to a focal blog channel to recommend a set of authors to follow. Such a system would be useful for brand managers interested in monitoring conversations about their products. Our reco...

As Internet usage and e-commerce grow, online social media serve as popular outlets for consumers to express sentiments about products. On Amazon, users can tag an album with a keyword, while tweets on Twitter represent a more natural conversation. The differing natures of these media make them difficult to compare. This project collects and analyz...

The phenomenal growth of social media, both in scale and importance, has created a unique opportunity to track information diffusion and the spread of influence, but can also make efficient tracking difficult. Given data streams representing blog posts on multiple blog channels and a focal query post on some topic of interest, our objective is to p...

Agent-based models can replicate real-world patterns, but finding parameters that achieve the best match can be difficult. To validate a model, a real-world dataset is often divided into a training set (to calibrate the parameters) and a test set (to validate the calibrated model). The difference between the training and test data and the simulated...

Bid shading is a common strategy in online auctions to avoid the "winner’s curse". While almost all bidders shade their bids, at least to some degree, it is impossible to infer the degree and volume of shaded bids directly from observed bidding data. In fact, most bidding data only allows us to observe the resulting price process, i.e. whether pric...

Agent-based modeling can illuminate how complex marketing phenomena emerge from simple decision rules. Marketing phenomena that are too complex for conventional analytical or empirical approaches can often be modeled using this approach. Agent-based modeling investigates aggregate phenomena by simulating the behavior of individual “agents,” such as...

Agent-based models (ABMs) provide a natural representation of large markets with many consumers interacting. As a result, business applications of these tools can provide powerful insights in to complex problems. When spatial and geographic modeling is added as well, these insights gain the ability to be transported to the real world, where challen...

Viral marketing mechanisms use the existing social network between customers to spread information about products and encourage product adoption. Existing viral marketing models focus on the dynamics of the diffusion process, however they typically: (a) only consider a single product campaign and (b) fail to model the evolution of the social networ...

The phenomenal growth in both scale and importance of social media such as blogs, micro-blogs and user-generated content, has created a need for tools that monitor information diffusion and make recommendations within these platforms. An essential element of social media, particularly blogs, is the hyperlink graph that connects various pieces of co...

The phenomenal growth of social media, both in scale and importance, has created a unique opportunity to track information diffusion and the spread of influence, but can also make efficient tracking difficult. Given data streams representing blog posts on multiple blog channels and a focal query post on some topic of interest, our objective is to p...

A defining property of the World Wide Web is a content site's ability to place virtually costless hyperlinks to third-party content as a substitute or complement to its own content. Costless hyperlinking has enabled new types of players, usually referred to as content aggregators, to successfully enter content ecosystems, attracting traffic and rev...

Does how much an agent thinks about its own actions affect the global properties of a system? We use the El Farol Bar Problem to investigate this question. In this model, the El Farol Bar represents a scarce resource. Does the amount of computational ability that agents possess affect resource utilization? For instance, if agents attend the bar ran...

Agent-based modeling has been extensively used by scientists to study complex systems. Participatory simulations are similar to agent-based models except that humans play the role of the virtual agents. The Bifocal modeling approach uses sensors to gather data about the real-world phenomena being modeled and uses that information to affect the mode...