Adriana M. J. B. de Carvalho

Learn More
We present text replays, a method for generating labels that can be used to train classifiers of student behavior. We use this method to label data as to whether students are gaming the system, within 20 intelligent tutor units on Algebra. Text replays are 2-6 times faster per label than previous methods for generating labels, such as quantitative field(More)
Gaming the system, attempting to succeed in an interactive learning environment by exploiting properties of the system rather than by learning the material (for example, by systematically guessing or abusing hints), is prevalent across many types of educational software. Past research on why students choose to game has focused on student individual(More)
Technology has the promise to transform educational prac-tices worldwide. In particular, cognitive tutoring systems are an example of educational technology that has been ex-tremely effective at improving mathematics learning over traditional classroom instruction. However, studies on the effectiveness of tutor software have been conducted mainly in the(More)
Gaming the system, a behavior where students disengage from a learning environment and attempt to succeed by exploiting properties of the system, has been shown to be associated with lower learning. Machine learned and knowledge engineered models have been created to identify gaming behaviors, but few efforts have been made to precisely identify how experts(More)
Recent research has shown that differences in software design and content are associated with differences in how much students game the system and go off-task. In particular the design features of a tutor have found to predict substantial amounts of variance in gaming and off-task behavior. However, it is not yet understood how this influence takes place.(More)
As education technology matures, researches debate whether data mining (EDM) or knowledge engineering (KE) paradigms are best for modeling complex learning constructs. A hybrid paradigm may capture strengths from both approaches. In particular, recent work has argued that successful data mining depends on thoughtful feature engineering. In this paper, we(More)
Cognitive tutoring systems have proven to be effective at improving mathematics learning in economically developed countries, but little is known about how teachers and students use these systems in other cultures. We visited three Latin American countries and observed use of the Middle School Mathematics Tutor in a school in each country. We found that(More)
We discuss a weekly afterschool program of environmental and sustainable development education for youth, given at an ecological reserve in Brazil. Students were guided to develop sustainable ways for the community to generate jobs and income, while preserving environmental heritage. Summary Currently, many communities in rural zones in the tropics are in(More)
Replicable research on the behavior known as gaming the system, in which students try to succeed by exploiting the functionalities of a learning environment instead of learning the material, has shown it is negatively correlated with learning outcomes. As such, many have developed models that can automatically detect gaming behaviors, towards deploying them(More)
As education technology matures, researches debate whether data mining (EDM) or knowledge engineering (KE) paradigms are best for modeling complex learning constructs. A hybrid paradigm may capture strengths from both approaches. In particular, recent work has argued that successful data mining depends on thoughtful feature engineering. In this paper, we(More)