Melanie Cooper

Learn More
This research describes a probabilistic approach for developing predictive models of how students learn problem-solving skills in general qualitative chemistry. The goal is to use these models to apply active, real-time interventions when the learning appears less than optimal. We first use self-organizing artificial neural networks to identify the most(More)
A total 31 psychoactive drugs were offered to groups of naive rats for IV self-administration and an injection rate greater than that for rats offered only saline indicated reinforcement. Two protocols were used: in the first, rats were offered drug at a selected dose for 5 days, then the dose was reduced by 1 log unit (to 0.1 the original dose) for an(More)
This paper describes a novel intelligent tutoring system called beSocratic, which targets question types that allow students to respond with free-form input but are able to be automatically evaluated and analyzed. Using beSocratic's GraphPad module, students are able to draw data structures using a mouse, touch, or a stylus. Once a student has completed a(More)
Using a combination of machine learning probabilistic tools, we have shown that some chemistry students fail to develop productive problem solving strategies through practice alone and will require interventions to continue making strategic progress. One particularly useful form of intervention was face-to-face collaborative learning which increased the(More)
Today, most higher education institutions use broad learning management systems such as Blackboard, Moodle, or Instructure Canvas to aid in assessment. Additionally, specialized systems (such as Mastering software series, OWL, etc.) exist for individual disciples and courses. While these systems have shown improvements in student learning, the majority of(More)
Data structures are one of the fundamental concepts that all computer scientist students must learn if they are to succeed in their careers. Therefore, it is important to develop and assess questions targeted at improving the teaching of data structures. Unfortunately, research suggests that multiple choice or matching questions cannot be used to properly(More)
We have developed models of how strategies are constructed and retained as male and female high school and university students gain experience in solving online qualitative chemical analysis problems. The most common strategies that students used when solving online problem-solving simulations were first classified using self-organizing artificial neural(More)
  • 1