Wordssuchasna0onna0onalna0onsshould

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: er year have blessed our country with plenty and with the means of a flourishing commerce. Text
mining
State
of
Union
Addresses
 Web
behavior
 •  All
speeches
in
one
large
plain
text
file
 •  Each
speech
starts
with
“***”
on
a
line
 followed
by
3
lines
of
informa0on
about
who
 gave
the
speech
and
when
 •  To
mine
the
speeches,
we
want
to
create
a
 word
vector
for
each
speech,
which
tracks
the
 counts
of
how
many
0mes
a
par0cular
word
 was
said
in
each
speech.
 •  Words
such
as
na0on,
na0onal,
na0ons
should
 collapse
to
the
same
“word”
 •  Every
0me
you
visit
a
Web
site,
informa0on
is
 recorded
about
the
visit:

 –  the
page
visited,

 –  date
and
0me
of
visit
 –  browser
used
 –  opera0ng
system
 –  IP
address
 2
 10/18/12
 Two
lines
of
the
Web
log
 169.237.46.168
‐
‐
...
View Full Document

This note was uploaded on 05/08/2013 for the course STAT 133 taught by Professor Staff during the Fall '08 term at University of California, Berkeley.

Ask a homework question - tutors are online