Results 1 - 10
of
23
Skill-based Mission Generation: A Data-driven Temporal Player Modeling Approach
"... Games often interweave a story and series of skill-based events into a complete sequence—a mission. An automated mission generator for skill-based games is one way to synthesize designer requirements with player differences to create missions tailored to each player. We argue for the need for predic ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
(Show Context)
Games often interweave a story and series of skill-based events into a complete sequence—a mission. An automated mission generator for skill-based games is one way to synthesize designer requirements with player differences to create missions tailored to each player. We argue for the need for predictive, data-driven player models that meet the requirements of: (1) predictive power, (2) accounting for temporal changes in player abilities, (3) accuracy in the face of little or missing player data, (4) efficiency with large sets of data, and (5) sufficiency for algorithmic generation. We present a tensor factorization approach to modeling and predicting player performance on skill-based tasks that meets the above requirements and a combinatorial optimization approach to mission generation to interweave an author’s preferred story structures and an author’s preferred player performance over a mission—a kind of difficulty curve—with modeled player performance. Categories and Subject Descriptors
Metrics for Evaluation of Student Models
, 2015
"... Researchers use many different metrics for evaluation of performance of student models. The aim of this paper is to provide an overview of commonly used metrics, to discuss properties, advantages, and disadvantages of different metrics, to summarize current practice in educational data mining, and t ..."
Abstract
-
Cited by 3 (2 self)
- Add to MetaCart
Researchers use many different metrics for evaluation of performance of student models. The aim of this paper is to provide an overview of commonly used metrics, to discuss properties, advantages, and disadvantages of different metrics, to summarize current practice in educational data mining, and to provide guidance for evaluation of student models. In the discussion we mention the relation of metrics to parameter fitting, the impact of student models on student practice (over-practice, under-practice), and point out connections to related work on evaluation of probability forecasters in other domains. We also provide an empirical comparison of metrics. One of the conclusion of the paper is that some commonly used metrics should not be used (MAE) or should be used more critically (AUC).
Analyzing student inquiry data using process discovery and sequence classification.
- In Proceedings of the 8th International Conference on Data Mining,
, 2015
"... ABSTRACT This paper reports on results of applying process discovery mining and sequence classification mining techniques to a data set of semi-structured learning activities. The main research objective is to advance educational data mining to model and support self-regulated learning in heterogen ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
ABSTRACT This paper reports on results of applying process discovery mining and sequence classification mining techniques to a data set of semi-structured learning activities. The main research objective is to advance educational data mining to model and support self-regulated learning in heterogeneous environments of learning content, activities, and social networks. As an example of our current research efforts, we applied temporal data mining analysis techniques to a PSLC DataShop data set
Using Factorization Machines for Student Modeling
"... Abstract. Predicting student performance (PSP), one of the task in Student Modeling, has been taken into account by educational data mining community recently. Previous works show that good results can be achieved by casting the PSP to rating prediction task in recommender systems, where students, t ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Abstract. Predicting student performance (PSP), one of the task in Student Modeling, has been taken into account by educational data mining community recently. Previous works show that good results can be achieved by casting the PSP to rating prediction task in recommender systems, where students, tasks and performance scores are mapped to users, items and ratings respectively, and thus, matrix factorization-one of the most prominent approaches for rating prediction task- is an appropriate choice. In this work, we propose using Factorization Machines which combine the advantages of Support Vector Machines with factorization models for the problem of PSP. Experiments on two large data sets show that this approach can improve the prediction results over the standard matrix factorization. 1
Linear Models of Student Skills for Static Data
"... Abstract. Current student skills models rely on non linear models such as Bayesian Networks and Bayesian Knowledge Tracing, and on general linear models, such as IRT which can be considered a logistic regression. Only a handful of recent studies have looked at linear models based on matrix factoriza ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Abstract. Current student skills models rely on non linear models such as Bayesian Networks and Bayesian Knowledge Tracing, and on general linear models, such as IRT which can be considered a logistic regression. Only a handful of recent studies have looked at linear models based on matrix factorization techniques. These studies obtained good success over data from dynamic student knowledge states when compared with widely used techniques such as Bayesian Knowledge Tracing. However, there are no reports of linear models applied to static knowledge states data. We introduce different linear models of student skill for small, static student test data that does not contain missing values. We compare their predictive performance the traditional psychometric Item Response Theory approach, and the k-nearest-neighbours approach that is widely used in recommender systems. The results show that that the IRT model is far better than all others. These results are somewhat unexpected given the recent relative success of factorization models for dynamic student test data. They raise the question of whether there is still a large amount of potential performance gain from other non-linear models for dynamic data. 1
Modeling Students ’ Learning and Variability of Performance in Problem Solving
"... Given data about problem solving times, how much can we automatically learn about students ’ and problems ’ characteristics? To address this question we extend a previously proposed model of problem solving times to include variability of students ’ performance and students ’ learning during sequenc ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Given data about problem solving times, how much can we automatically learn about students ’ and problems ’ characteristics? To address this question we extend a previously proposed model of problem solving times to include variability of students ’ performance and students ’ learning during sequence of problem solving tasks. We evaluate proposed models over simulated data and data from a “Problem Solving Tutor”. The results show that although the models do not lead to substantially improved predictions, the learnt parameter values are meaningful and capture useful information about students and problems. 1.
Tutor Modeling vs. Student Modeling
"... The current paradigm in student modeling, Knowledge Tracing, has continued to show the power of its simplifying assumption of knowledge as a binary and monotonically increasing construct, the value of which directly causes the outcome of student answers to questions. Recent efforts have focused on o ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
The current paradigm in student modeling, Knowledge Tracing, has continued to show the power of its simplifying assumption of knowledge as a binary and monotonically increasing construct, the value of which directly causes the outcome of student answers to questions. Recent efforts have focused on optimizing the prediction accuracy of responses to questions using student models. Incorporating individual student parameter interactions has been an interpretable and principled approach which has improved the performance of this task, as demonstrated by its application in the 2010 KDD Cup challenge on Educational Data. Performance prediction, however, can have limited practical utility. The greatest utility of such student models can be their ability to model the tutor and the attributes of the tutor which are causing learning. Harnessing the same simplifying assumption of learning used in student modeling, we can turn this model on its head to effectively tease out the tutor attributes causing learning and begin to optimize the tutor model to benefit the student model.
Evaluation of a Personalized Method for Proactive Mind Wandering Reduction
"... Abstract. We report on a project with the goal of creating a proactive system that attempts to reduce the propensity to mind wander (MW) by optimizing learning conditions (e.g., text difficulty and value) for individual learners. Our previous work had shown that supervised classification based on in ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Abstract. We report on a project with the goal of creating a proactive system that attempts to reduce the propensity to mind wander (MW) by optimizing learning conditions (e.g., text difficulty and value) for individual learners. Our previous work had shown that supervised classification based on individual at-tributes could be used to detect the learning condition with the lowest MW rates. Here we test the model by comparing MW rates for the predicted optimal conditions to MW rates from a random control condition or in the condition with the overall best MW rate across all learners. Our results suggest that our method is better than these non-adaptive alternatives in certain contexts.
A Framework for User
, 2016
"... This paper presents an approach to user modeling in QuizMASter, a multi-user educational game shows that uses multi-agent systems to create a personalized learning environment. To keep the students motivated during the games, the system creates, maintains, and uses models of all attending contestant ..."
Abstract
- Add to MetaCart
(Show Context)
This paper presents an approach to user modeling in QuizMASter, a multi-user educational game shows that uses multi-agent systems to create a personalized learning environment. To keep the students motivated during the games, the system creates, maintains, and uses models of all attending contestants (i.e., learners). Taking advantage of prominent student modeling techniques with some novel ideas, we propose a structure and procedure to create student models and combined student models in QuizMASter. These models are used to create an adaptive environment in the quiz games, selecting and posing questions whose levels of difficulty closely match the knowledge levels of game contestants in certain areas of knowledge; meaning that the game questions for each game are adjusted to the knowledge levels of the learners and the game does not provide too easy or too difficult questions for the contestants. By selecting properly challenging questions for each game show, students are expected to stay motivated and continue for citations:
A Framework for User Modeling in QuizMASter Journal of e-Learning and Knowledge Society
"... This paper presents an approach to user modeling in QuizMASter, a multi-user educational game shows that uses multi-agent systems to create a personalized learning environment. To keep the students motivated during the games, the system creates, maintains, and uses models of all attending contestant ..."
Abstract
- Add to MetaCart
(Show Context)
This paper presents an approach to user modeling in QuizMASter, a multi-user educational game shows that uses multi-agent systems to create a personalized learning environment. To keep the students motivated during the games, the system creates, maintains, and uses models of all attending contestants (i.e., learners). Taking advantage of prominent student modeling techniques with some novel ideas, we propose a structure and procedure to create student models and combined student models in QuizMASter. These models are used to create an adaptive environment in the quiz games, selecting and posing questions whose levels of difficulty closely match the knowledge levels of game contestants in certain areas of knowledge; meaning that the game questions for each game are adjusted to the knowledge levels of the learners and the game does not provide too easy or too difficult questions for the contestants. By selecting properly challenging questions for each game show, students are expected to stay motivated and continue for citations:
