Author
Yoshitaka Matsumoto
Bio: Yoshitaka Matsumoto is an academic researcher from Ritsumeikan University. The author has contributed to research in topics: Hidden Markov model & Psychology. The author has an hindex of 3, co-authored 5 publications receiving 54 citations.
Papers
More filters
••
01 Sep 2004TL;DR: The experimental results given in this paper show that Hidden Markov Models have higher recognition performance than the previous approach, especially for classification of players of different types but having similar action frequencies.
Abstract: In this paper, we describe our work on classification of players in Massively Multiplayer Online Games using Hidden Markov Models based on player action sequences. In our previous work, we have discussed a classification approach using a variant of Memory Based Reasoning based on player action frequencies. That approach, however, does not exploit time structures hidden in action sequences of the players. The experimental results given in this paper show that Hidden Markov Models have higher recognition performance than our previous approach, especially for classification of players of different types but having similar action frequencies.
28 citations
01 Jan 2003
TL;DR: This paper addresses the challenge of identification of player types in massively multiplayer online games (MMOGs) and demonstrates the approach using a PC.
Abstract: In this paper, we discuss an approach for identification of player types inmassively multiplayer online games (MMOGs). MMOGs provide fast growingonlinecommunities(Jarettet al.2003).Managingalarge-scalecommunityim-plies many challenges, such as identification of player types, social structures,and virtual economic mechanisms, etc. In this paper, we address the challengeonidentificationofplayertypes.AsafirststeptowarduseofrealMMOGdata,we demonstrate our approach using a PC
14 citations
01 Jan 2003
TL;DR: An effective approach for player identification is discussed, the results of which can be exploited for CRM of MMOGs, and a feature extraction method is proposed that is based on the frequency of each type of game items acquired by each player.
Abstract: The market of massively multiplayer online games (MMOGs) is expanding rapidly. MMOG business can be considered as eBusiness where CRM (Customer Relationship Management) is a key factor of success. This paper discusses an effective approach for player identification, the results of which can be exploited for CRM of MMOGs. A feature extraction method is proposed that is based on the frequency of each type of game items acquired by each player. To validate the proposed feature extraction method, experiments are conducted using game log data obtained from an MMOG simulator. The experimental results show that the proposed feature extraction method outperforms a method, previously proposed by the same authors, that is based on the frequency of each type of actions performed by each player.
8 citations
••
01 Jan 2005TL;DR: This chapter presented an efiective approach for identification of user types in virtual worlds and AMBR, adopted as the classifier, could successfully identify the type of unknown user agents and could give higher performance with the item-based features.
Abstract: In this chapter we have presented an efiective approach for identification of user types in virtual worlds. Two types of input features were discussed, action-based features and item-based features. The former type uses the information on the frequency of each type of action that each user performed. The latter one uses the information on the frequency of each type of item that each user acquired. AMBR, adopted as the classifier, could successfully identify the type of unknown user agents. In addition, it could give higher performance with the item-based features. In future work, we plan to conduct experiments using agents with more complicated behaviors and to investigate use of order information in either action sequences or item sequences. Eventually, we will apply our findings to real user data.
3 citations
01 Jan 2005
TL;DR: The resulting HMMs have recognition performance higher than those initialized either by random setting of parameters or by assigning an equivalent value to all parameters in a same parameter set, and comparable to those using a prior knowledge.
Abstract: In this paper, we propose a method for determining the model structure and the initial parameters of Hidden Markov Models (HMMs) used for classification of players in Massively Multiplayer Online Games (MMOGs). The concept of the proposed method is that of mapping important features of each player type to its HMM states. Such important features are extracted by N -Gram and a variant of Term Frequency, techniques in Natural Language Processing. In our previous work, we discussed the use of HMMs for the aforementioned classification task. However, in the experiments there the model structure and the initial parameters of HMMs were determined using a priori knowledge on the player models of the MMOG simulator in use. With the proposed method in the present paper, the resulting HMMs have recognition performance higher than those initialized either by random setting of parameters or by assigning an equivalent value to all parameters in a same parameter set. In addition, they are comparable to those using a prior knowledge.
1 citations
Cited by
More filters
••
19 Sep 2007TL;DR: This paper proposes a new biometric for human identification based on users' game-play activities, and proposes the RET scheme, which is based on the KullbackLeibler divergence between idle time distributions, for user identification.
Abstract: Account hijacking is considered one of the most serious security problems in online games A hijacker normally takes away valuable virtual items from the stolen accounts, and trades those items for real money Even though account hijacking is not uncommon, there is currently no general solutions to determine whether an account has been hijacked The game company is not aware of a hijack unless it is reported by the victim However, it is usually too late---usually a hijacker already took away anything valuable when a user finds that his/her account has been stolenIn this paper, we propose a new biometric for human identification based on users' game-play activities Our main summary are two-fold: 1) we show that the idle time distribution is a representative feature of game players; 2) we propose the RET scheme, which is based on the KullbackLeibler divergence between idle time distributions, for user identification Our evaluations shows that the RET scheme achieves higher than 90% accuracy with a 20-minute detection time given a 200-minute history size
58 citations
••
TL;DR: The most relevant trends and directions of research in personalisation for computer games, a true multi-disciplinary problem requiring contributions from areas as diverse as artificial and computational intelligence, game studies, psychology, game design, and human–computer interaction are surveyed.
43 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
••
01 Sep 2004TL;DR: The experimental results given in this paper show that Hidden Markov Models have higher recognition performance than the previous approach, especially for classification of players of different types but having similar action frequencies.
Abstract: In this paper, we describe our work on classification of players in Massively Multiplayer Online Games using Hidden Markov Models based on player action sequences. In our previous work, we have discussed a classification approach using a variant of Memory Based Reasoning based on player action frequencies. That approach, however, does not exploit time structures hidden in action sequences of the players. The experimental results given in this paper show that Hidden Markov Models have higher recognition performance than our previous approach, especially for classification of players of different types but having similar action frequencies.
28 citations
••
06 Apr 2010TL;DR: A meta-classification approach that breaks the clustering of gameplay mixed data into three levels of analysis and applies a combination of social network analysis metrics to social data to find clusters in the players' social network is proposed.
Abstract: Player classification has recently become a key aspect of game design in areas such as adaptive game systems, player behaviour prediction, player tutoring and non-player character design. Past research has focused on the design of hierarchical, preferencebased and probabilistic models aimed at modelling players' behaviour. We propose a meta-classification approach that breaks the clustering of gameplay mixed data into three levels of analysis. The first level uses dimensionality reduction and partitional clustering of aggregate game data in an action/skillbased classification. The second level applies similarity-based clustering of action sequences to group players according to their preferences. For this we propose a new approach which uses Rubner’s Earth Mover’s Distance (EMD) as a similarity metric to compare histograms of players’ game world explorations. The third level applies a combination of social network analysis metrics, such as shortest path length, to social data to find clusters in the players' social network. We test our approach in a gameplay dataset from a freely available first-person social hunting game.
28 citations