In this article we describe the emerging area of text classification research focused on the problem of collaborative learning process analysis both from a broad perspective and more specifically in terms of a new publicly available tool set called TagHelper tools. Analyzing the variety of different facets of learners’ interaction that are important for their learning is a time consuming and effortful process. Improving automated analyses of such highly valued processes of collaborative learning by adapting and applying recent text classification technologies would make it a less arduous task to obtain insights from corpus data. It also holds the potential for enabling substantially improved on-line instruction both by providing teachers and facilitators with reports about the groups they are moderating and by scaffolding technology as in the emerging area of context sensitive collaborative learning support triggered dynamically on an as-needed basis. In this article, we report on an interdisciplinary research project, which has been investigating the effectiveness of applying text classification technology to a large CSCL discourse corpus that had been analyzed by human coders using a theory-based multi-dimensional coding scheme. We report promising results and include an in-depth discussion of important issues such as reliability, validity, and efficiency that should be considered when deciding on the appropriateness of adopting a new technology such as TagHelper tools.

Abstract. The research reported in this paper focuses on the hypothesis that an intelligent tutoring system that provides guidance with respect to students ' meta-cognitive abilities can help them to become better learners. Our strategy is to extend a Cognitive Tutor (Anderson, Corbett, Koedinger, & Pelletier, 1995) so that it not only helps students acquire domain-specific skills, but also develop better general help-seeking strategies. In developing the Help Tutor, we used the same Cognitive Tutor technology at the metacognitive level that has been proven to be very effective at the cognitive level. A key challenge is to develop a model of how students should use a Cognitive Tutor's help facilities. We created a preliminary model, implemented by 57 production rules that capture both effective and ineffective help-seeking behavior. As a first test of the model's efficacy, we used it off-line to evaluate students ' help-seeking behavior in an existing data set of student-tutor interactions. We then refined the model based on the results of this analysis. Finally, we conducted a pilot study with the Help Tutor involving four students. During one session, we saw a statistically significant reduction in students ' meta-cognitive error rate, as determined by the Help Tutor's model. These preliminary results inspire confidence as we gear up for a larger-scale controlled experiment to evaluate whether tutoring on help seeking has a positive effect on students' learning outcomes. Keywords. Meta-cognition, cognitive modeling, help seeking, tutor agents, educational log file analysis

rk over a period of time. Describing problems students encounter as they engage in inquiry and finding ways to ameliorate those problems has received considerable attention recently (Hmelo & Williams, [Special Issue, JLS], 1998; McGilly, 1994, Blumenfeld et al, 1998). In this paper, we describe inquiry in more detail, discuss ways to aid students via instructional, curriculum, and 1 . In Minstell, J. Van Zee, E. (Eds.) Inquiry into inquiry: Science learning and Teaching, American Association for the Advancement of Science Press, Washington, D.C. (in press). 2 The authors would like to thank Ann Rivet from the University of Michigan for her helpful editorial comments. 11/4/98 page 2 technological supports, and then illustrate how these have been applied to specific phases on inquiry where students encounter difficulties. What Is Inquiry And Why Use It? Broadly conceived inquiry refers to the diverse ways in which scientists stu

Some of the recent electronic learning environments have moved beyond the conventional delivery of text, multimedia, and objective tests. There are systems with animated conversational agents, intelligent adaptive tutoring, interactive simulations, and other features designed to engage learners and promote deeper comprehension. One system is AutoTutor, a learning environment that tutors students by holding a conversation in natural language. AutoTutor’s design was inspired by explanation-based constructivist theories of learning, intelligent tutoring systems that adaptively respond to student knowledge, and empirical research on dialogue patterns in tutorial discourse. AutoTutor presents challenging questions and then engages in mixed initiative dialogue that guides the student in building an answer. It provides feedback to the student on what the student types in (positive, neutral, negative feedback), pumps the student for more information, prompts the student to fill in missing words, gives hints, fills in missing information, identifies and

Abstract. Cognitive Tutors are proven effective learning environments, but are still not as effective as one-on-one human tutoring. We describe an environment (ALPS) designed to engage students in question-asking during problem solving. ALPS integrates Cognitive Tutors with Synthetic Interview (SI) technology, allowing students to type free-form questions and receive pre-recorded video clip answers. We performed a Wizard-of-Oz study to evaluate the feasibility of ALPS and to design the question-and-answer database for the SI. In the study, a human tutor played the SI’s role, reading the students ’ typed questions and answering over an audio/video channel. We examine the rate at which students ask questions, the content of the questions, and the events that stimulate questions. We found that students ask questions in this paradigm at a promising rate, but there is a need for further work in encouraging them to ask deeper questions that may improve knowledge encoding and learning. 1

It is well-documented that most students do not have adequate proficiencies in inquiry and metacognition, particularly at deeper levels of comprehension that require explanatory reasoning. The proficiencies are not routinely provided by teachers and normal tutors so it is worthwhile to turn to computer-based learning environments. This article describes some of our recent computer systems that were designed to facilitate explanation-centered learning through strategies of inquiry and metacognition while students learn science and technology content. Point&Query augments hypertext, hypermedia, and other learning environments with question–answer facilities that are under the learner control. AutoTutor and iSTART use animated conversational agents to scaffold strategies of inquiry, metacognition, and explanation construction. AutoTutor coaches students in generating answers to questions that require explanations (e.g., why, what-if, how) by holding a mixed-initiative dialogue in natural language. iSTART models and coaches students in constructing self-explanations and in applying other metacomprehension strategies while reading text. These systems have shown promising results in tests of learning gains and learning strategies. Imagine an active, curious, self-regulated learner who asks

Based on an engagement perspective of reading development, we investigated the extent to which an instructional framework of combining motivation support and strategy instruction (Concept-Oriented Reading Instruction—CORI) influenced reading outcomes for third-grade children. In CORI, five motivational practices were integrated with six cognitive strategies for reading comprehension. In the first study, we compared this framework to an instructional framework emphasizing Strategy Instruction (SI), but not including motivation support. In the second study, we compared CORI to SI and to a traditional instruction group (TI), and used additional measures of major constructs. In both studies, class-level analyses showed that students in CORI classrooms were higher than SI and/or TI students on measures of reading comprehension, reading motivation, and reading strategies. A widespread goal of education in the elementary grades is reading comprehension for all students. Reading comprehension becomes especially important in the later elementary grades (Sweet & Snow, 2003) and provides the basis for a substantial amount of learning in secondary school (Kirsch et al., 2002). Without the skills of reading comprehension and the motivation

The opinions and positions expressed in this practice guide are the authors ’ and do not necessarily represent the opinions and positions of the Institute of Education Sciences or the U.S. Department of Education. This practice guide should be reviewed and applied according to the specific needs of the educators and education agencies using it and with full realization that it represents only one approach that might be taken, based on the research that was available at the time of publication. This practice guide should be used as a tool to assist in decision-making rather than as a “cookbook.” Any references within the document to specific education products are illustrative and do not imply endorsement of these products to the exclusion of other products that are not referenced. U.S. Department of Education

Third through fifth grade adequate decoders who were poor comprehenders were trained for 10 weeks in either the verbally based reciprocal teaching (RT) program (n = 22) or the visually based visualizing/ verbalizing (V/V) program (n = 23), or they were assigned to an untreated control group (n = 14). Training reading comprehension strategies in small groups enhanced comprehension as the experimental groups made significant gains on 11 measures, whereas the untreated control group made only 1 significant gain. Between experimental group comparisons (yielding effect sizes>.32) favored the RT group on several measures that depend on explicit, factual material, while the V/V group was favored on several visually mediated measures. Regarding which experimental condition was statistically optimal, the RT group made only 1 significantly greater gain than the V/V group on answering text-explicit open-ended questions. This study was designed to determine whether teaching poor text comprehenders reading strategies in a small group format would improve their reading comprehension and to evaluate whether they would demonstrate differential gains depending on whether they were placed in a verbally based or primarily visually

Abstract not found