Search

This paper addresses the problem of inferring students’ strategies when they interact with data-modeling software used for pedagogical purposes. The software enables students to learn about statistical data by building and analyzing their own models. Automatic recognition of students’ activities when interacting with pedagogical software is challenging. Students can pursue several plans in parallel and interleave the execution of these plans. The algorithm presented in this paper decomposes students’ complete interaction histories with the software into hierarchies of interdependent tasks that may be subsequently compared with ideal solutions. This algorithm is evaluated empirically using commercial software that is used in many schools. Results indicate that the algorithm is able to (1) identify the plans students use when solving problems using the software; (2) distinguish between those actions in students’ plans that play a salient part in their problem-solving and those representing exploratory actions and mistakes; and (3) capture students’ interleaving and free-order action sequences., Engineering and Applied Sciences

With increasing frequency, computer agents participate in collaborative and competitive multiagent domains in which humans reason strategically to make decisions. The deployment of computer agents in such domains requires that the agents understand something about human behavior so that they can interact successfully with people; the computer agents must be sensitive to how people reason in strategic settings as well as to the social utilities people employ to inform their reasoning. To date, these design requirements for computer agents have received relatively little attention. To further research in this area, we are developing the Colored Trails (CT) testbed [5], a configurable and extensible open-source system for use by the research community at large to investigate multiagent decision making., Engineering and Applied Sciences

Many environments in which people and computer agents interact involve deploying resources to accomplish tasks and satisfy goals. This paper investigates the way that the context in which decisions are made affects the behavior of people and the performance of computer agents that interact with people in such environments. It presents experiments that measured negotiation behavior in two different types of settings. One setting was a task context that made explicit the relationships among goals, (sub)tasks and resources. The other setting was a completely abstract context in which only the payoffs for the decision choices were listed. Results show that people are more helpful, less selfish, and less competitive when making decisions in task contexts than when making them in completely abstract contexts. Further, their overall performance was better in task contexts. A predictive computational model that was trained on data obtained in the task context outperformed a model that was trained under the abstract context. These results indicate that taking context into account is essential for the design of computer agents that will interact well with people., Engineering and Applied Sciences

Human annotation of discourse corpora typically results in segmentation hierarchies that vary in their degree of agreement. This paper presents several techniques for unifying multiple discourse annotations into a single hierarchy, deemed a “gold standard ” — the segmentation that best captures the underlying linguistic structure of the discourse. It proposes and analyzes methods that consider the level of embeddedness of a segmentation as well as methods that do not. A corpus containing annotated hierarchical discourses, the Boston Directions Corpus, was used to evaluate the “goodness” of each technique, by comparing the similarity of the segmentation it derives to the original annotations in the corpus. Several metrics of similarity between hierarchical segmentations are computed: precision/recall of matching utterances, pairwise inter-reliability scores ( ¡), and non-crossing-brackets. A novel method for unification that minimizes conflicts among annotators outperforms methods that require consensus among a majority for the ¡ and recall metrics, while capturing much of the structure of the discourse. When higher recall is preferred, methods requiring a majority are preferable to those that demand full consensus among annotators., Engineering and Applied Sciences