The Andes Physics Tutoring System: Lessons Learned

By Kurt VanLehn, Collin Lynch, Kay G. Schulze, J. Shapiro, R. Shelby, Linwood Taylor, Donald Treacy, Anders Weinstein, M. Wintersgill. International Journal of Artificial Intelligence in Education, 2005

627 citations recorded by the source corpus.

The Andes system demonstrates that student learning can be significantly increased by upgrading only their homework problem-solving support. Although Andes is called an intelligent tutoring system, it actually replaces only the students' pencil and paper as they do problem-solving homework. Students do the same problems as before, study the same textbook, and attend the same lectures, labs and recitations. Five years of experimentation at the United States Naval Academy indicates that Andes significantly improves student learning. Andes' key feature appears to be the grain-size of interaction. Whereas most tutoring systems have students enter only the answer to a problem, Andes has students enter a whole derivation, which may consist of many steps, such as drawing vectors, drawing coordinate systems, defining variables and writing equations. Andes gives feedback after each step. When the student asks for help in the middle of problem-solving, Andes gives hints on what's wrong with an incorrect step or on what kind of step to do next. Thus, the grain size of Andes' interaction is a single step in solving the problem, whereas the grain size of a typical tutoring system's interaction is the answer to the problem. This report is a comprehensive description of Andes. It describes Andes' pedagogical principles and features, the system design and implementation, the evaluations of pedagogical effectiveness, and our plans for dissemination.

Subfields: Artificial Intelligence, Computer Science Applications, Media Technology

View Paper: https://www.semanticscholar.org/paper/9279f0c083bc0859daf42427a876788a84ed784f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Science Applications

In Media Technology

Citations in the corpus

AutoTutor and affective autotutor: Learning by talking with cognitively and emotionally intelligent computers that talk back (2012, background): “…is, the Cognitive Tutors, [Aleven et al. 2006; Anderson et al. 1995; Corbett 2002; Koedinger and Corbett 2006], physics such as AutoTutor, Andes, Atlas,and Why/Atlas [VanLehn et al. 2007; VanLehn et al. 2005], electronics [Lesgold et al. 1992], and information technology [Mitrovic et al. 2007].”
Feedback Strategies for Interactive Learning Tasks (2007, methodology): “, 1999), on error analysis (VanLehn, 1990), and on tutoring techniques (Anderson et al., 1995; McKendree, 1990; Merrill et al., 1992; VanLehn et al., 2005).”
A New Paradigm for Intelligent Tutoring Systems: Example-Tracing Tutors (2009, background): “Whereas model-tracing tutors, Cognitive Tutors included (Koedinger et al., 1997; VanLehn et al., 2005), interpret and assess student behavior with reference to a cognitive model that can solve problems in the way that competent students can, and whereas constraint-based tutors (Mitrovic & Ohlsson,…”
Effectiveness of Intelligent Tutoring Systems (2016, background): “Finally, VanLehn et al. (2005) reported results from 5 years of use of the Andes tutoring system at the U.S. Naval Academy.”
The Faces of Engagement: Automatic Recognition of Student Engagementfrom Facial Expressions (2014, background): “games, intelligent tutoring systems (ITS) [4], [30], [43], [52], and massively open online courses (MOOCs).”
Exploring the Assistance Dilemma in Experiments with Cognitive Tutors (2007, methodology): “In effect, the intelligent novice condition helped students rationalize, like the derivations in the self-explanation model by VanLehn et al. (1992) , why their misconceptions do not work.”
Focus on Formative Feedback (2008, background): “The cost of conducting extensive error analyses and cognitive diagnosis may not provide sufficient benefit to learning (Sleeman et al., 1989; VanLehn et al., 2005).”
The ASSISTments Ecosystem: Building a Platform that Brings Scientists and Teachers Together for Minimally Invasive Research on Human Learning and Teaching (2014, background): “Van Lehn’s (VanLehn et al. 2005) Lesson Learned paper points out that all systems involve thousands of little design decisions; not all of them can be shared.”
The Relative Effectiveness of Human Tutoring, Intelligent Tutoring Systems, and Other Tutoring Systems (2011, background): “For instance, in 4 year-long evaluations, the learning gains of students who used a step-based physics tutoring system were d = 0.61 higher than the learning gains of students who did the same homework assignments on paper (VanLehn et al., 2005).”
Multimodal semi-automated affect detection from conversational cues, gross body language, and facial features (2010, background): “…the reasons behind student errors, and mastery learning through assessments of the probability that the student knows each skill relevant to the system (Anderson et al. 1995, 2005; Gertner and VanLehn 2000; Graesser et al. 2005, 2001; Koedinger et al. 1997; VanLehn 1990; VanLehn et al. 2005).”
The Behavior of Tutoring Systems (2006, methodology): “Outer loop: The Andes physics tutoring system (http://www.andes.pitt.edu/) helps students learn how to solve physics problems (K. VanLehn et al., 2005; K. VanLehn et al., 2002).”
Stupid Tutoring Systems, Intelligent Humans (2016, methodology): “…Tutors use production-rule models to represent skill (Anderson et al. 1995), ALEKS uses prerequisite hierarchies to represent the connections between items (Falmagne et al. 2013), and SQL-Tutor uses extensive constraint-based models to represent appropriate performance (Mitrovic and Ohlsson 1999).”
Synthesis of Discipline-Based Education Research in Physics. (2014, result): “Physics Education Research - 33 Studies comparing paper-and-pencil homework to web-based homework have found mixed results, with some studies citing no differences in performance (Bonham, Deardorff, & Beichner, 2003) and others citing improved performance with web-based tutors or homework systems (C”