[Vision2020] The Book That Listens

[Art Deco]

  My New Scientist


<http://www.newscientist.com/article/mg21528765.700-the-intelligent-textbook-that-helps-students-learn.html>
 The 'intelligent textbook' that helps students learn

   - 01 August 2012 by *Michael
Reilly*<http://www.newscientist.com/search?rbauthors=Michael+Reilly>
   - Magazine issue 2876 <http://www.newscientist.com/issue/2876>. *Subscribe
   and save*<http://subscribe.newscientist.com/bundles.aspx?promcode=6005&term=1Y&intcmp=SUBS-nsarttop>

  *Want to know more about your subject? Type in your own question and
artificially intelligent software will construct a new page to answer your
query*

SITTING down with the Inquire system is, at first, a lot like trying to
cosy up to an intimidatingly dense biology textbook. Sure, its presentation
on the iPad is slick, but that can't hide the fact that you are in for a
tough old read.

That is until you highlight the first bit of particularly impenetrable
text. Suddenly a list of questions pops up in the right-hand margin. Touch
one and you are whisked away to a Wikipedia-like page full of information
specific to the concept you are stuck on. Terms like "chloroplast" and
"plasma membrane" are succinctly defined, and the page explains how each
concept fits into the wider field of biology.

Want to know more? Type in your own question and artificially intelligent
software will construct a new page to answer your query.

The aim of Inquire <http://inquireproject.com/> is to provide students with
the world's first intelligent textbook, says its creator David Gunning of
Seattle-based Vulcan<http://www.vulcan.com/TemplateCompany.aspx?contentId=54>.
At first glance, the system just looks like an electronic version of *Campbell
Biology*<http://www.amazon.com/Campbell-Biology-Edition-Jane-Reece/dp/0321558235>,
the tome that forms the bedrock of biology classes for first-year
university and advanced high school students in the US. But behind the
scenes is a machine-readable concept map of the 5000 or so ideas covered in
the book, along with information on how they are all related.

When a student asks a question - "what does a protein do?", for instance -
the system first converts it into a more structured query, such as "what is
the function of a protein?", and then uses this to search and find results
from the concept map.

Earlier this year, the team recruited 72 first-year students from De Anza
College <http://www.deanza.edu/> in Cupertino, California, to put the
system to the test. Students were given either the full Inquire system, the
Inquire system with the query function switched off, or a paper copy
of *Campbell
Biology*. They were then asked to spend 60 minutes reading a section of the
book, 90 minutes on homework problems, and to take a 20-minute-long quiz.

Students who used the full Inquire system scored a grade better on the
quiz, on average, than the other groups. "When we did our assessment, we
didn't see any Ds or Fs, which we did see in the control groups," says
Debbie Frazier, a high school biology teacher who works on the project.
"Our students could use Inquire as a tool and ask it questions that they
might be embarrassed to ask a teacher in person because it makes them feel
stupid."

A video on the work was presented at the Conference on Artificial
Intelligence <http://www.aaai.org/Conferences/AAAI/aaai12.php> in Toronto,
Canada, last week.

While such results are promising, perhaps it's a little soon to crown
Inquire the future of textbooks. For starters, after two years of work the
system is still only half-finished. The team plan to encode the rest of the
1400-page *Campbell Biology* by the end of 2013, but they expect a team of
18 biologists will be needed to do so. This raises concerns about whether
the project could be expanded to cover other areas of science, let alone
other subjects.

Still, adhering to the textbook format makes sense because it means
students won't have to wade through reams of irrelevant information, as
they do when searching the web, says Benedict du
Boulay<http://www.sussex.ac.uk/Users/bend/cv/frameshomepage.html>of
the University of Sussex in Brighton, UK.

Such habits are common, says Inquire team member Adam
Overholtzer<http://www.ai.sri.com/people/overholt/>,
of SRI International in Menlo Park, California. "I'm not going to name
names, but all of the students go to Wikipedia to study," he says. "It's
open while they are reading their books."
 Rise of the markerbots

Engineering students are often asked to sketch structures to show they
understand certain concepts. Grading such sketches can be overwhelming for
tutors, who may preside over 1000 students on a course. So Stephanie
Valentine of Texas A&M University and her team have developed
Mechanix<http://srlweb.cse.tamu.edu/srlng/research/project/18>,
artificially intelligent software that grades sketches. First, the tutor
draws the correct answer into the system, which recognises the image and
the maths behind it. This is then compared to students' responses. An
intelligent tutor also gives students guidance as they draw. In tests on
122 students at Texas A&M, those who used Mechanix performed 15 per cent
better on an assignment.


-- 
Art Deco (Wayne A. Fox)
art.deco.studios at gmail.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.fsr.com/pipermail/vision2020/attachments/20120805/9010d1ec/attachment.html>