iSTART: Interactive strategy training for active reading and thinking

Abstract

Interactive Strategy Training for Active Reading and Thinking (iSTART) is a Web-based application that provides young adolescent to college-age students with high-level reading strategy training to improve comprehension of science texts. iSTART is modeled after an effective, human-delivered intervention called self-explanation reading training (SERT), which trains readers to use active reading strategies to self-explain difficult texts more effectively. To make the training more widely available, the Web-based trainer has been developed. Transforming the training from a human-delivered application to a computer-based one has resulted in a highly interactive trainer that adapts its methods to the performance of the students. The iSTART trainer introduces the strategies in a simulated classroom setting with interaction between three animated characters-an instructor character and two student characters-and the human trainee. Thereafter, the trainee identifies the strategies in the explanations of a student character who is guided by an instructor character. Finally, the trainee practices self-explanation under the guidance of an instructor character. We describe this system and discuss how appropriate feedback is generated.

Computer-based assessment of student-constructed responses

“…While we have advocated the use of hybrid systems, this review did not provide specific recommendations regarding how to develop improved systems. There are relatively few systems that use hybrid approaches to date (Britt et al, 2004;Cai et al, 2011;Graesser & McNamara 2012;McNamara et al, 2004), and each focuses on different types of protocols. We do know that the shorter responses require well-engineered word spotting in the expectations, with large gains from structured regular expressions and ngrams.…”

“…Think-aloud and self-explanation responses (Bråten & Strømsø, 2003;Chi, de Leeuw, Chiu, & LaVancher, 1994;Coté, Goldman, & Saul, 1998;McNamara et al, 2004;Trabasso & Magliano, 1996) and dialogues between tutee and tutor (Graesser, Person, & Magliano, 1995) are examples of meaningmaking student responses that have been investigated in the cognitive sciences and have been implemented in computer systems during the last 15 years. The developers have the goal of assessing and providing feedback on both the content and dynamic processes of learning and comprehension.…”

“…We define student-constructed responses as those that require a student to produce an answer in natural language that may range from a couple of sentences to several paragraphs. These advances have been in the context of computer-based assessments of explanations and think-aloud protocols during reading comprehension (Gilliam, Magliano, Millis, Levinstein, & Boonthum, 2007;Magliano, Millis, the RSAT Development Team, Levinstein, & Boonthum, 2011), the grading of essays and text summaries (Attali & Burstein, 2006;Burstein, Marcu, & Knight, 2003;Franzke, Kintsch, Caccamise, Johnson, & Dooley, 2005;Landauer, Laham, & Foltz, 2003), the grading of short-answer questions (Leacock & Chodorow, 2003), and intelligent tutoring systems and trainers that require students to produce constructed responses during interactive conversations (Graesser, Jeon, & Dufty, 2008;Litman et al, 2006;McNamara, Levinstein, & Boonthum, 2004;VanLehn et al, 2007). These can take the form of directed responses to specific questions or less directed thinkaloud and self-explanation responses.…”

Supporting Students in the Analysis of Case Studies for Professional Ethics Education

“…Although not a typical use, LSA "in the small" has been utilized for evaluating students' answers against predefined system answers in several ITSs including Autotutor [28], iSTART [64], and R-SAT [22]. We also employed LSA in our system for this purpose, making use of the Gensim library [76] implementation of LSA with stopwords removed and a similarity threshold ranging between 0.5-0.85.…”

Academic Press is an imprint of Elsevier

“…Similar to propositional analyses of text that lay out the concepts related to a particular text, latent semantic analysis (LSA) uses computer technology to provide a fully automatic method to look at semantic coherence (e.g., Foltz, Kintsch, & Landauer, 1998), looking at repetition of words, but also synonyms, antonyms, and other words that tend to be used in similar contexts. LSA is a model of how human knowledge is represented as well as an extremely useful tool that has been applied to produce automated strategy trainers (e.g., iSTART: McNamara, Levinstein, & Boonthum, 2004;ITTS: Wijekumar & Meyer, in press). Such training could be of use in teaching comprehension strategies to older readers.…”