Mining the Web for Feelings, Not Facts

Computers may be good at crunching numbers, but can they crunch feelings?

The rise of blogs and social networks has fueled a bull market in personal opinion: reviews, ratings, recommendations and other forms of online expression. For computer scientists, this fast-growing mountain of data is opening a tantalizing window onto the collective consciousness of Internet users.

An emerging field known as sentiment analysis is taking shape ... Full Story »

Posted by Fabrice Florin - via Hiroko Tabuchi, Publish2 (Business), New York Times (Most Emailed)
Tags Help
Stats Help
# Diggs: 1 (as of 2009-08-23)
Editorial Help
Posted by: Posted by Fabrice Florin - Aug 23, 2009 - 8:41 PM PDT
Content Type: Article
Edit Lock: This story can be edited
Edited by: Fabrice Florin - Aug 24, 2009 - 10:15 AM PDT

Reviews

Show All | Notes | Comments | Quotes | Links
Christine Ahlstrom
4.4
by Christine Ahlstrom - Sep. 29, 2009

I thought this was a really great article. It is relevant to today's technologically advanced society and it provides really interesting insight into the ways in which computers fall short of the human brain and how people are trying to make computers more "human". I'm really interested in the human psyche and I think this article ties in the complexities of human nature and speech patterns (i.e. sarcasm) that can't necessarily be recognized by computers, even if they are "trained" to look for those subtleties.

See Full Review » (11 answers)
Fabrice Florin
3.6
by Fabrice Florin - Aug. 24, 2009
See Full Review » (4 answers)
Jaclyn Reardon
3.5
by Jaclyn Reardon - Sep. 17, 2009

Social networking is obviously fast growing and it doesn't seem like it's going to stop like its said in the article. I think it is a good thing overall allowing people to express their opinions and network in a new way. There are the good and bad sides of it of course but I think its a great thing.

See Full Review » (19 answers)

Comments on this story Help (BETA)

NT Rating | My Rating

Ratings

3.7

Good
from 3 reviews (24% confidence)
Quality
3.7
Facts
4.0
Fairness
4.5
Information
3.0
Insight
4.0
Sourcing
4.5
Style
4.5
Accuracy
4.0
Balance
4.0
Context
3.0
Depth
3.3
Enterprise
3.5
Expertise
3.0
Originality
3.0
Relevance
5.0
Transparency
3.0
Responsibility
4.0
Popularity
3.5
Recommendation
3.7
Credibility
4.3
# Reviews
1.5
# Views
5.0
# Likes
1.0
# Emails
1.0
More
How our ratings work »
(See these related stories.)

Links Help

No links yet. Please review this story to add some!