@article{
 title = {Behavlets: a Method for Practical Player Modelling using Psychology-Based Player Traits and Domain Specific Features},
 type = {article},
 year = {0},
 id = {21cf7587-2d1e-3cbc-8f06-50863473d6f8},
 created = {2012-01-24T14:52:31.000Z},
 file_attached = {false},
 profile_id = {2b061976-e572-3810-9e28-7dd7c12775ee},
 last_modified = {2015-08-29T17:01:30.000Z},
 tags = {IF>1,Journal},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Cowley},
 source_type = {Journal Article},
 abstract = {As player demographics broaden it has become important to appreciate variation in player types. Improved player models can help game designers create games that accommodate a range of play styles/preferences, and may also facilitate the design of systems that detect player type and adapt dynamically in real-time. Existing approaches can model players, but most focus on tracking and classifying behaviour based on simple functional metrics such as deaths, specific choices, player avatar attributes, and completion times. We describe a different approach which seeks to leverage expert domain knowledge using a theoretical framework linking behaviour and game design patterns. The aim is to derive features of play from sequences of actions which are intrinsically informative about behaviour – which, because they are directly interpretable, we name ‘behavlets’. We present the theoretical underpinning of this approach from research areas including psychology, temperament theory, player modelling, and game composition. The behavlet creation process is described in detail; illustrated using a clone of the well-known game Pac-Man, with data gathered from 100 participants. An evaluation study is presented with a further 35 participants, comparing two player-move prediction algorithms based on Decision Theory. One uses a standard metric-based approach to calculate player utilities from the look-ahead tree of game states; the contrasting behavlet-based version improves accuracy of move predictions from 39% to 71%, above the random chance level of 36%. We conclude that the behavlet approach has significant promise, is complementary to existing methods and can improve theoretical validity of player models.},
 bibtype = {article},
 author = {Cowley, Benjamin and Charles, Darryl},
 journal = {under review User Modeling and User-Adapted Interaction}
}

{"_id":"JgtmLgWJk9pQhGNfi","bibbaseid":"cowley-charles-behavletsamethodforpracticalplayermodellingusingpsychologybasedplayertraitsanddomainspecificfeatures","downloads":0,"creationDate":"2015-08-29T17:02:58.843Z","title":"Behavlets: a Method for Practical Player Modelling using Psychology-Based Player Traits and Domain Specific Features","author_short":["Cowley, B.","Charles, D."],"year":0,"bibtype":"article","biburl":null,"bibdata":{"title":"Behavlets: a Method for Practical Player Modelling using Psychology-Based Player Traits and Domain Specific Features","type":"article","year":0,"id":"21cf7587-2d1e-3cbc-8f06-50863473d6f8","created":"2012-01-24T14:52:31.000Z","file_attached":false,"profile_id":"2b061976-e572-3810-9e28-7dd7c12775ee","last_modified":"2015-08-29T17:01:30.000Z","tags":"IF>1,Journal","read":false,"starred":false,"authored":"true","confirmed":"true","hidden":false,"citation_key":"Cowley","source_type":"Journal Article","abstract":"As player demographics broaden it has become important to appreciate variation in player types. Improved player models can help game designers create games that accommodate a range of play styles/preferences, and may also facilitate the design of systems that detect player type and adapt dynamically in real-time. Existing approaches can model players, but most focus on tracking and classifying behaviour based on simple functional metrics such as deaths, specific choices, player avatar attributes, and completion times. We describe a different approach which seeks to leverage expert domain knowledge using a theoretical framework linking behaviour and game design patterns. The aim is to derive features of play from sequences of actions which are intrinsically informative about behaviour – which, because they are directly interpretable, we name ‘behavlets’. We present the theoretical underpinning of this approach from research areas including psychology, temperament theory, player modelling, and game composition. The behavlet creation process is described in detail; illustrated using a clone of the well-known game Pac-Man, with data gathered from 100 participants. An evaluation study is presented with a further 35 participants, comparing two player-move prediction algorithms based on Decision Theory. One uses a standard metric-based approach to calculate player utilities from the look-ahead tree of game states; the contrasting behavlet-based version improves accuracy of move predictions from 39% to 71%, above the random chance level of 36%. We conclude that the behavlet approach has significant promise, is complementary to existing methods and can improve theoretical validity of player models.","bibtype":"article","author":"Cowley, Benjamin and Charles, Darryl","journal":"under review User Modeling and User-Adapted Interaction","bibtex":"@article{\n title = {Behavlets: a Method for Practical Player Modelling using Psychology-Based Player Traits and Domain Specific Features},\n type = {article},\n year = {0},\n id = {21cf7587-2d1e-3cbc-8f06-50863473d6f8},\n created = {2012-01-24T14:52:31.000Z},\n file_attached = {false},\n profile_id = {2b061976-e572-3810-9e28-7dd7c12775ee},\n last_modified = {2015-08-29T17:01:30.000Z},\n tags = {IF>1,Journal},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {true},\n hidden = {false},\n citation_key = {Cowley},\n source_type = {Journal Article},\n abstract = {As player demographics broaden it has become important to appreciate variation in player types. Improved player models can help game designers create games that accommodate a range of play styles/preferences, and may also facilitate the design of systems that detect player type and adapt dynamically in real-time. Existing approaches can model players, but most focus on tracking and classifying behaviour based on simple functional metrics such as deaths, specific choices, player avatar attributes, and completion times. We describe a different approach which seeks to leverage expert domain knowledge using a theoretical framework linking behaviour and game design patterns. The aim is to derive features of play from sequences of actions which are intrinsically informative about behaviour – which, because they are directly interpretable, we name ‘behavlets’. We present the theoretical underpinning of this approach from research areas including psychology, temperament theory, player modelling, and game composition. The behavlet creation process is described in detail; illustrated using a clone of the well-known game Pac-Man, with data gathered from 100 participants. An evaluation study is presented with a further 35 participants, comparing two player-move prediction algorithms based on Decision Theory. One uses a standard metric-based approach to calculate player utilities from the look-ahead tree of game states; the contrasting behavlet-based version improves accuracy of move predictions from 39% to 71%, above the random chance level of 36%. We conclude that the behavlet approach has significant promise, is complementary to existing methods and can improve theoretical validity of player models.},\n bibtype = {article},\n author = {Cowley, Benjamin and Charles, Darryl},\n journal = {under review User Modeling and User-Adapted Interaction}\n}","author_short":["Cowley, B.","Charles, D."],"bibbaseid":"cowley-charles-behavletsamethodforpracticalplayermodellingusingpsychologybasedplayertraitsanddomainspecificfeatures","role":"author","urls":{},"downloads":0},"search_terms":["behavlets","method","practical","player","modelling","using","psychology","based","player","traits","domain","specific","features","cowley","charles"],"keywords":[],"authorIDs":[]}