Muhammad Aurangzeb Ahmad

Mining for Gold Farmers: Automatic Detection of Deviant Players in MMOGs

Gold farming refers to the illicit practice of gathering and selling virtual goods in online games for real money. Although around one million gold farmers engage in gold farming related activities, to date a systematic study of identifying gold farmers has not been done. In this paper we use data from the massively-multiplayer online role-playing game (MMORPG) EverQuest II to identify gold farmers. We perform an exploratory logistic regression analysis to identify salient descriptive statistics followed by a machine learning binary classification problem to identify a set of features for classification purposes. Given the cost associated with investigating gold farmers, we also give criteria for evaluating gold farming detection techniques, and provide suggestions for future testing and evaluation techniques.

The Social Behaviors of Experts in Massive Multiplayer Online Role-Playing Games

We examine the social behaviors of game experts in Everquest II, a popular massive multiplayer online role-playing game (MMO). We rely on exponential random graph models (ERGM) to examine the anonymous privacy-protected social networks of 1,457 players over a five-day period. We find that those who achieve the most in the game send and receive more communication, while those who perform the most efficiently at the game show no difference in communication behavior from other players. Both achievement and performance experts tend to communicate with those at similar expertise levels, and higher-level experts are more likely to receive communication from other players.

Link Prediction Across Multiple Social Networks

The problem of link prediction has been studied extensively in literature. There are various versions of the link prediction problem \textit{e.g.,} link existence problem, link removal problem, predicting edge weights over time etc. In this paper we describe a new type of link prediction problem called the Inter-network link-prediction problem where the task is to predict links \textit{across} different networks. Thus given a set of nodes which participate in multiple networks the task is to determine if one can predict the edges that occur in one network by only using node attribute and edge information from other networks. We use insights from theories of evolution of social communication networks and the MTML framework to derive models which can be used to make link predictions across networks. For the experiments data from different \textit{types} of social networks from a Massively Multiplayer Online Role Playing Game (MMORPG) is used.

Inferring Player Rating from Performance Data in Massively Multiplayer Online Role-Playing Games (MMORPGs)

This paper examines online player performance in EverQuest II, a popular massively multiplayer online role-playing game (MMORPG) developed by Sony Online Entertainment. The study uses the games player performance data to devise performance metrics for online players. We report three major findings. First, we show that the games point-scaling system overestimates performances of lower level players and underestimates performances of higher level players. We present a novel point-scaling system based on the games player performance data that addresses the underestimation and overestimation problems. Second, we present a highly accurate predictive model for player performance as a function of past behavior. Third, we show that playing in groups impacts individual performance and that player-level characteristics alone are insufficient in explaining an individuals performance, which calls for a different set of performance metrics methods.

The Many Faces of Mentoring in an MMORPG

Mentoring refers to the phenomenon where a more skilled or knowledgeable person helps a less skilled or less knowledgeable person gain skill in a particular domain. In this paper we study the phenomenon of mentoring in a massive multiplayer online role-playing game (MMORPG). We identify four different types of mentoring, which map to several important motivational features. We then measure the social networks of mentors at multiple levels, and propose a network model to describe the emergence and evolution of mentoring.

What can gold farmers teach us about criminal networks

By observing how covert financial networks operate in online games like World of Warcraft, we can learn about how they might function offline.

An Ant Colony Optimization Approach to Expert Identification in Social Networks

In a social network there may be people who are experts on a subject. Identifying such people and routing queries to such experts is an important problem. While the degree of separation between any node and an expert node may be small, assuming that social networks are small world networks, not all nodes may be willing to route the query because flooding the network with queries may result in the nodes becoming less likely to route queries in the future. Given this constraint and that there may be time constraints it is imperative to have an efficient way to identify experts in a network and route queries to these experts. In this paper we present an Ant Colony Optimization (ACO) based approach for expert identification and query routing in social networks. Also, even after one has identified the experts in the network, there may be new emerging topics for which there are not identifiable experts in the network. For such cases we extend the basic ACO model and introduce the notion of composibility of pheromones, where trails of different pheromones can be combined to for routing purposes.

Exploration of Robust Features of Trust Across Multiple Social Networks

In this paper, we investigate the problem of trust formation in virtual world interaction networks. The problem is formulated as one of link prediction, intranet work and internet work, in social networks. We use two datasets to study the problem - SOEs Ever quest II MMO game dataset and IBMs Small Blue sentiments dataset. We explore features based on the nodes individual properties as well as based on the nodes location within the network. In addition, we take into account the nodes participation in other social networks within a specific prediction task. Different machine learning models built on the features are evaluated with the goal of finding a common set of features which are both robust and discriminating across the two datasets. Shortest Distance and Sum of Degree are found to be robust, discriminating features across the two datasets. Finally, based on experiment results and observations, we provide insights into the underlying online social processes. These insights can be extended to models for online social trust.

Trust Me, I'm an Expert: Trust, Homophily and Expertise in MMOs

Trust is a ubiquitous phenomenon in social networks and people trust one another for a variety of reasons. In this paper we study the problem of trust in massively multiplayer online games (MMOs) with respect to homophily and expertise. We prose a topology of homophily in MMOs based on the literature on homophily and domain knowledge of MMOs. Our results show that while there is some mapping between homophily in MMOs and the theories of homophily in the offline world, the mapping is not complete. Only ascribed homophily and value homophily is observed in the trust network, while other types of homophilies are conspicuously absent. We observed that the trust network exhibits many properties which are not observed in most other social networks. Based on our observations we propose a generative model for trust networks in MMOs.

Robust features of trust in social networks

We identify robust features of trust in social networks; these are features which are discriminating yet uncorrelated and can potentially be used to predict trust formation between agents in other social networks. The features we investigate are based on an agent’s individual properties as well as those based on the agent’s location within the network. In addition, we analyze features which take into account the agent’s participation in other social interactions within the same network. Three datasets were used in our study—Sony Online Entertainment’s EverQuest II game dataset, a large email network with sentiments and the publicly available Epinions dataset. The first dataset captures activities from a complex persistent game environment characterized by several types of in-game social interactions, whereas the second dataset has anonymized information about people’s email and instant messaging communication. We formulate the problem as one of the link predictions, intranetwork and internetwork, in social networks. We first build machine learning models and then perform an ablation study to identify robust features of trust. Results indicate that shared skills and interests between two agents, their level of activity and level of expertise are the top three predictors of trust in a social network. Furthermore, if only network topology information were available, then an agent’s propensity to connect or communicate, the cosine similarity between two agents and shortest distance between them are found to be the top three predictors of trust. In our study, we have identified the generic characteristics of the networks used as well as the features investigated so that they can be used as guidelines for studying the problem of predicting trust formation in other social networks.