scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Classification of Online Game Players Using Action Transition Probability and Kullback Leibler Entropy

20 Mar 2007-Journal of Advanced Computational Intelligence and Intelligent Informatics (Fuji Technology Press Ltd.)-Vol. 11, Iss: 3, pp 319-326
TL;DR: This paper proposes a new player classification approach using action transition probability and Kullback Leibler entropy, which performed better than an existing approach based on action frequency and comparably to another existing approach using the Hidden Markov Model.
Abstract: Online game players are more satisfied with contents tailored to their preferences. Player classification is necessary for determining which classes players belong to. In this paper, we propose a new player classification approach using action transition probability and Kullback Leibler entropy. In experiments with two online game simulators, Zereal and Simac, our approach performed better than an existing approach based on action frequency and comparably to another existing approach using the Hidden Markov Model (HMM). Our approach takes into account both the frequency and order of player action. While HMM performance depends on its structure and initial parameters, our approach requires no parameter settings.

Content maybe subject to copyright    Report

Citations
More filters
Journal ArticleDOI
TL;DR: This work shows how incorporating more information about players than their raw skill can lead to more balanced matches, and presents a strategy to explicitly maximize the players' fun, taking advantage of a rich player profile that includes information about player behavior and personal preferences.
Abstract: Player satisfaction is particularly difficult to ensure in online games, due to interactions with other players. In adversarial multiplayer games, matchmaking typically consists in trying to match together players of similar skill level. However, this is usually based on a single-skill value, and assumes the only factor of “fun” is the game balance. We present a more advanced matchmaking strategy developed for Ghost Recon Online, an upcoming team-focused first-person shooter (FPS) from Ubisoft (Montreal, QC, Canada). We first show how incorporating more information about players than their raw skill can lead to more balanced matches. We also argue that balance is not the only factor that matters, and present a strategy to explicitly maximize the players' fun, taking advantage of a rich player profile that includes information about player behavior and personal preferences. Ultimately, our goal is to ask players to provide direct feedback on match quality through an in-game survey. However, because such data were not available for this study, we rely here on heuristics tailored to this specific game. Experiments on data collected during Ghost Recon Online's beta tests show that neural networks can effectively be used to predict both balance and player enjoyment.

75 citations

Journal ArticleDOI
TL;DR: This work presents a real-time classifier of player type, implemented in the test-bed game Pac-Man, and analyzes the concept descriptions learned by the Decision Trees.
Abstract: The power of using machine learning to improve or investigate the experience of play is only beginning to be realised. For instance, the experience of play is a psychological phenomenon, yet common psychological concepts such as the typology of temperaments have not been widely utilised in game design or research. An effective player typology provides a model by which we can analyse player behaviour. We present a real-time classifier of player type, implemented in the test-bed game Pac-Man. Decision Tree algorithms CART and C5.0 were trained on labels from the DGD player typology (Bateman and Boon, 21st century game design, vol. 1, 2005). The classifier is then built by selecting rules from the Decision Trees using a rule- performance metric, and experimentally validated. We achieve ~70% accuracy in this validation testing. We further analyse the concept descriptions learned by the Decision Trees. The algorithm output is examined with respect to a set of hypotheses on player behaviour. A set of open questions is then posed against the test data obtained from validation testing, to illustrate the further insights possible from extended analysis.

24 citations

Journal ArticleDOI
TL;DR: Results indicate that the Haar wavelet transform is effective in classification when the k-nearest neighbor classifier is used to classify players based on dynamic time warping distances between reconstructed sequences.
Abstract: Online game players’ action sequences, while important to understand their behavior, usually contain noise and/or redundancy, making them unnecessarily long. To acquire briefer sequences representative of players’ features, we apply the Haar wavelet transform to action sequences and reconstruct them from selected wavelet coefficients. Results indicate that this approach is effective in classificationwhen the k-nearest neighbor classifier is used to classify players based on dynamic time warping distances between reconstructed sequences.

5 citations


Cites background from "Classification of Online Game Playe..."

  • ...Keywords: online game, player classification, wavelet transform, dynamic time warping, action sequences...

    [...]

01 Aug 2011
TL;DR: An improved methodology for classifying players (identifying deviant players such as terrorists) through multivariate analysis of data from avatar characteristics and behaviors in massive multiplayer online games (MMOGs) is developed.
Abstract: : The purpose of our research is to develop an improved methodology for classifying players (identifying deviant players such as terrorists) through multivariate analysis of data from avatar characteristics and behaviors in massive multiplayer online games (MMOGs). To build our classification models, we developed three significant enhancements to the standard Generalized Regression Neural Networks (GRNN) modeling method. The first enhancement is a feature selection technique based on GRNNs, allowing us to tailor our feature set to be best modeled by GRNNs. The second enhancement is a hybrid GRNN which allows each feature to be modeled by a GRNN tailored to its data type. The third enhancement is a spread estimation technique for large data sets that is faster than exhaustive searches, yet more accurate than a standard heuristic. We applied our new techniques to a set of data from the MMOG, Everquest II, to identify deviant players ('gold farmers'). The identification of gold farmers is similar to labeling terrorists in that the ratio of gold farmer to standard player is extremely small, and the in-game behaviors for a gold farmer have detectable differences from a standard player. Our results were promising given the difficulty of the classification process, primarily the extremely unbalanced data set with a small number of observations from the class of interest. As a screening tool our method identifies a significantly reduced set of avatars and associated players with a much improved probability of containing a number of players displaying deviant behaviors. With further efforts at improving computing efficiencies to allow inclusion of additional features and observations with our framework, we expect even better results.

2 citations

Journal ArticleDOI
TL;DR: Machine learning approaches to player modeling and Latent Dirichlet Allocation, Latent Semantic Analysis, Low-Level Feature Representation, Player Modeling.
Abstract: Machine learning approaches to player modeling traditionally employ a high-level game-knowledge-based feature for representing game sessions, and often player behavioral features as well. The present work makes use of generic low-level features and latent semantic analysis for unsupervised player modeling, but mostly for revealing underlying hidden information regarding game semantics that is not easily detectable beforehand.

2 citations

References
More filters
Journal ArticleDOI
Lawrence R. Rabiner1
01 Feb 1989
TL;DR: In this paper, the authors provide an overview of the basic theory of hidden Markov models (HMMs) as originated by L.E. Baum and T. Petrie (1966) and give practical details on methods of implementation of the theory along with a description of selected applications of HMMs to distinct problems in speech recognition.
Abstract: This tutorial provides an overview of the basic theory of hidden Markov models (HMMs) as originated by L.E. Baum and T. Petrie (1966) and gives practical details on methods of implementation of the theory along with a description of selected applications of the theory to distinct problems in speech recognition. Results from a number of original sources are combined to provide a single source of acquiring the background required to pursue further this area of research. The author first reviews the theory of discrete Markov chains and shows how the concept of hidden states, where the observation is a probabilistic function of the state, can be used effectively. The theory is illustrated with two simple examples, namely coin-tossing, and the classic balls-in-urns system. Three fundamental problems of HMMs are noted and several practical techniques for solving these problems are given. The various types of HMMs that have been studied, including ergodic as well as left-right models, are described. >

21,819 citations

Book
10 Jun 1997
TL;DR: One of the first practical guides to mining business data, Data Mining Techniques describes techniques for detecting customer behavior patterns useful in formulating marketing, sales, and customer support strategies.
Abstract: From the Publisher: Data Mining Techniques thoroughly acquaints you with the new generation of data mining tools and techniques and shows you how to use them to make better business decisions. One of the first practical guides to mining business data, it describes techniques for detecting customer behavior patterns useful in formulating marketing, sales, and customer support strategies. While database analysts will find more than enough technical information to satisfy their curiosity, technically savvy business and marketing managers will find the coverage eminently accessible. Here's your chance to learn all about how leading companies across North America are using data mining to beat the competition; how each tool works, and how to pick the right one for the job; seven powerful techniques - cluster detection, memory-based reasoning, market basket analysis, genetic algorithms, link analysis, decision trees, and neural nets, and how to prepare data sources for data mining, and how to evaluate and use the results you get. Data Mining Techniques shows you how to quickly and easily tap the gold mine of business solutions lying dormant in your information systems.

1,823 citations

Book
08 Feb 1996
TL;DR: This book presents a detailed formulation of neural networks from the information-theoretic viewpoint, and shows how these methods may be applied to the topics of supervised and unsupervised learning, including feature extraction, linear and nonlinear independent component analysis, and Boltzmann machines.
Abstract: From the Publisher: Neural networks provide a powerful new technology to model and control nonlinear and complex systems. In this book, the authors present a detailed formulation of neural networks from the information-theoretic viewpoint. They show how this perspective provides new insights into the design theory of neural networks. In particular, they show how these methods may be applied to the topics of supervised and unsupervised learning, including feature extraction, linear and nonlinear independent component analysis, and Boltzmann machines. Readers are assumed to have a basic understanding of neural networks, but all of the relevant concepts from information theory are carefully introduced and explained. Consequently, readers from several different scientific disciplines - notably, cognitive scientists, engineers, physicists, statisticians, and computer scientists - will find this book to be a very valuable contribution to this topic.

292 citations


"Classification of Online Game Playe..." refers background in this paper

  • ...Keywords: player classification, online game, data mining, customer relationship management, game design...

    [...]

Journal ArticleDOI
Ruck Thawonmas, Shigeo Abe1
01 Apr 1997
TL;DR: A novel approach to feature selection based on analysis of class regions which are generated by a fuzzy classifier, where a subset of features that has the lowest sum of the exception ratios has the tendency to contain the most relevant features, compared to the other subsets with the same number of features.
Abstract: This paper presents a novel approach to feature selection based on analysis of class regions which are generated by a fuzzy classifier. A measure for feature evaluation is proposed and is defined as the exception ratio. The exception ratio represents the degree of overlaps in the class regions, in other words, the degree of having exceptions inside of fuzzy rules generated by the fuzzy classifier. It is shown that for a given set of features, a subset of features that has the lowest sum of the exception ratios has the tendency to contain the most relevant features, compared to the other subsets with the same number of features. An algorithm is then proposed that performs elimination of irrelevant features. Given a set of remaining features, the algorithm eliminates the next feature, the elimination of which minimizes the sum of the exception ratios. Next, a terminating criterion is given. Based on this criterion, the proposed algorithm terminates when a significant increase in the sum of the exception ratios occurs due to the next elimination. Experiments show that the proposed algorithm performs well in eliminating irrelevant features while constraining the increase in recognition error rates for unknown data of the classifiers in use.

75 citations

01 Jan 2003
TL;DR: A conceptual software agent architecture for supporting users of mobile commerce services will be presented, including a peer-to-peer based collaborative filtering extension to support product and service recommendations and the proposed incremental classifier is shown to an order of magnitude faster than the other classifiers.
Abstract: Cyberspace plays an increasingly important role in people’s life due to its plentiful offering of services and information, e.g. the Word Wide Web, the Mobile Web and Online Games. However, the usability of cyberspace services is frequently reduced by its lack of customization according to individual needs and preferences.In this thesis we address the cyberspace customization issue by focusing on methods for user representation and prediction. Examples of cyberspace customization include delegation of user data and tasks to software agents, automatic pre-fetching, or pre-processing of service content based on predictions. The cyberspace service types primarily investigated are Mobile Commerce (e.g. news, finance and games) and Massively Multiplayer Online Games (MMOGs).First a conceptual software agent architecture for supporting users of mobile commerce services will be presented, including a peer-to-peer based collaborative filtering extension to support product and service recommendations.In order to examine the scalability of the proposed conceptual software agent architecture a simulator for MMOGs is developed. Due to their size and complexity, MMOGs can provide an estimated “upper bound” for the performance requirements of other cyberspace services using similar agent architectures.Prediction of cyberspace user behaviour is considered to be a classification problem, and because of the large and continuously changing nature of cyberspace services there is a need for scalable classifiers. This is handled by proposed classifiers that are incrementally trainable, support a large number of classes, and supports efficient decremental untraining of outdated classification knowledge, and are efficiently parallelized in order to scale well.Finally the incremental classifier is empirically compared with existing classifiers on: 1) general classification data sets, 2) user clickstreams from an actual web usage log, and 3) a synthetic game usage log from the developed MMOG simulator. The proposed incremental classifier is shown to an order of magnitude faster than the other classifiers, significantly more accurate than the naive bayes classifier on the selected data sets, and with insignificantly different accuracy from the other classifiers.The papers leading to this thesis have combined been cited more than 50 times in book, journal, magazine, conference, workshop, thesis, whitepaper and technical report publications at research events and universities in 20 countries. 2 of the papers have been applied in educational settings for university courses in Canada, Finland, France, Germany, Norway, Sweden and USA.

36 citations