The mission of the ARTSI (Advancing Robotics Technology for Societal Impact) Alliance, a consortium of 19 Historically Black Colleges and Universities (HBCUs) and 9 major research universities (R1s), is to enlarge the nation’s engineering and science talent pool by increasing the number of students from underrepresented groups who pursue advanced training in computer science. ARTSI is one of several alliances funded by the National Science Foundation’s Broadening Participation in Computing Program. ARTSI focuses specifically on institutions serving African Americans and uses robotics education to attract and engage students. In this paper we describe the activities comprising ARTSI, our vision of a robotics curriculum for CS undergraduates, and ways to integrate robotics modules into existing CS courses.

In this paper, we present a Personalized Intelligent Tutoring System that uses Reinforcement Learning techniques to implicitly learn teaching rules and provide instructions to students based on their needs. The system works on coarsely labeled data with minimum expert knowledge to ease extension to newer domains.

In this work we hypothesize that giving students a reflective reading after spoken dialog tutoring in qualitative physics will improve learning. The reading is designed to help students compare similar aspects of previously tutored problems, and to abstract their commonalities. We also hypothesize that student motivation will affect how well the text is processed, and so influence learning. We find that the beneficial effects of the reflective text significantly interact with motivation, such that moderately motivated students learn significantly more from the reflective text than from a non-reflective control text. More poorly or highly motivated students did not benefit from reflective text. These results demonstrate that implicit reflection can improve learning after dialog tutoring with a qualitative physics tutor. They further demonstrate that this result can be obtained with a reflective/abstractive text without recourse to dialog, and that the effectiveness of the text is sensitive to the motivation level of the student.

This study investigates Serious Games (SG) to assess motivational factors appropriate to an Intelligent Tutoring System (ITS). An ITS can benefit from SG’ elements that can highly support learners’ motivation. Thus, identifying and assessing the effect that these factors may have on learners is a crucial step before attempting to integrate them into an ITS. We designed an experiment using a Serious Game and combined both the theoretical ARCS model of motivation and empirical physiological sensors (heart rate, skin conductance and EEG) to assess the effects of motivational factors on learners. We then identified physiological patterns correlated with one motivational factor in a Serious Game (Alarm triggers) associated with the Attention category of the ARCS model. The best result of three classifiers run on the physiological data has reached an accuracy of 73.8% in identifying learners’ attention level as being either above or below average. These results open the door to the possibility for an ITS to discriminate between attentive and inattentive learners.

It is widely acknowledged that one-on-one human tutoring is one of the most effective ways to provide learning, however, the source of its effectiveness is still unclear. Tutor-centered, student-centered, and interaction hypotheses have been proposed as possible explanations of the effectiveness of human tutoring. Most research has addressed this question by analyzing tutorial sessions at the dialogue move or speech act level. The present paper adopts a different approach by focusing on word usage patterns in 50 naturalistic tutorial sessions between human students and expert tutors. Specifically, each unique word in the session was designated as a student initiative word, a tutor initiative word, or a shared-initiative word. Comparisons of the frequencies as well as the weights of the words assigned to each of these categories indicated that the student and tutor share initiative even though the tutor’s are considerably more verbose. The implications of the results for the development of an ITS that aspires to model expert tutors are discussed.

Creating natural language tutorial dialogue systems that realize effective strategies is a central challenge for intelligent tutoring systems research. Traditional approaches generally require large development time, do not generalize well across domains, and do not match the flexibility and natural language sophistication of human tutors. A promising approach that may offer several benefits is data-driven system development, in which a dialogue policy is learned from corpora of human tutorial dialogue. To date these learning approaches typically focus on optimizing the tutor’s choice of act, and do not explicitly model the instances in which the tutor chose not to act. This paper reports on a hidden Markov modeling (HMM) approach within human textual tutorial dialogue that explicitly represents the tutors’ choices not to intervene. The results show that an HMM that models tutor non-interventions predicts tutor moves significantly better than a model that does not explicitly represent the non-interventions. The findings have implications for automatically modeling tutorial strategies and for learning dialogue policies from corpora.

The New York Public Library is participating in the Chronicling America initiative to develop an online searchable database of historically significant newspaper articles. Microfilm copies of the papers are scanned and high resolution OCR software is run on them. The text from the OCR provides a wealth of data and opinion for researchers and historians. However, the categorization of articles provided by the OCR engine is rudimentary and a large number of the articles are labeled ``editorial" without further categorization. To provide a more refined grouping of articles, unsupervised machine learning algorithms (such as K-Means) are being investigated. The K-Means algorithm requires tuning of parameters such as the number of clusters and mechanism of seeding to ensure that the search is not prone to being caught in a local minima. We designed a pilot study to observe whether humans are adept at finding sub-categories. The subjective labels provided by humans are used as a guide to compare performance of the automated clustering techniques. In addition, seeds provided by annotators are carefully incorporated into a semi-supervised K-Means algorithm (Seeded K-Means); empirical results indicate that this helps to improve performance and provides an intuitive sub-categorization of the articles labeled ``editorial" by the OCR engine.

Community mining is applied in order to identify groups of users which share, e.g., common interests or expertise. This paper presents an approach for mining descriptive patterns in order to characterize communities in terms of their distinctive features: For an efficient discovery approach, we introduce optimistic estimates for obtaining an upper bound for the community quality. We present an evaluation using data from the real-world social bookmarking system BibSonomy.

We have experimented with the notion of — conceptualization, and contextualization from situated cognition and psychic reflection from activity theory for identifying context into a method called the activity states framework (ASF). The purpose of the ASF is to provide a method of analysis for identifying collaborators activity during situated context − specific to Web-mediated collaboration. This paper introduces the ASF.

We discuss and evaluate metrics for difficulty rating of Sudoku puzzles. The correlation coefficient with human performance for our best metric is 0.95. The data on human performance were obtained from three web portals and they comprise thousands of hours of human solving over 2000 problems. We provide a simple computational model of human solving activity and evaluate it over collected data. Using the model we show that there are two sources of problem difficulty: complexity of individual steps (logic operations) and structure of dependency among steps. Beside providing a very good Sudoku-tuned metric, we also discuss a metric with few Sudoku-specific details, which still provides good results (correlation coefficient is 0.88). Hence we believe that the approach should be applicable to difficulty rating of other constraint satisfaction problems.