Post on 03-Aug-2020
Eric Gilbert | Tony Bergstrom | Karrie Karahalios | University of Illinois
BLOGS ARE ECHO CHAMBERS:BLOGS ARE ECHO CHAMBERS
Are blogs echo chambers? Do blogs cut readers off from dissenting opinions?
Negroponte1996
Sunstein2002
Sunstein2008
“ It’s hardly possible to overstate the value, in the present state of human improvement, of placing human beings in contact with other persons dissimilar to themselves, and with modes of thought and action unlike those with which they are familiar.
John Stuart MillPrinciples of Political Economy, 1848
”
112 M blogsas measured by Technorati, Jun 2009
Are blogs echo chambers? Do blogs cut readers off from dissenting opinions?
Political bloggers link to like-minded bloggers.
Adamic & Glance 2005
Hargittai & Gallo 2008
Groups often adopt extreme viewpoints.
Baron & Hoppe 1996
Sechrist & Stangor 2001
RELATED WORK
5 blog genres
33 top blogs
1,094 blog comments
OUR DATASET
Technology
2 TechCrunch
3 Gizmodo
4 Engadget
23 Kotaku
30 Scobelizer
35 Gigaom
37 TUAW
44 Joystiq
45 Threat Level
# Technorati rank Apr 08
Political
1 Huffington Post
11 Daily Kos
26 Think Progress
41 Crooks & Liars
58 NewsBusters
Entertainment
5 Boing Boing
13 Gawker
20 Perez Hilton
31 Valleywag
36 Neatorama
42 Slashfilm
Lifestyle
6 Life Hacker
29 Consumerist
32 uthink
45 Zenhabits
38 Dooce
53 Sartorialist
Meta
10 ReadWriteWeb
18 Dosh Dosh
21 ProBlogger
27 Copyblogger
34 ShoeMoney
43 Daily Blog Tips
71 Matt Cutts
Great post and I really like the video. is is extremely similar to the approach I use in writing almost anything …
“
Just wait until hackers exploit the print layer to this mesh stuff enough to grab root and start injecting python code …
“
ProBlogger
Scobelizer
Cohen’s κ = 0.71 pointwise = 0.74
Inter-rater reliability
agree
neither
disagree85 103 2246 26
2
Wald methodp < 0.05
neither
agree 39.2%
Proportions of agreement
11.1%disagree
49.4%
χ2(8, N=979) = 86.3p < 0.001
Agreement proportions by genre
tech
enter.
lifestyle
politics
meta
63% neither 24% agree 13%
63% 24% 13%
44% 51% 5
40% 47% 13%
33% 55% 12%
ALGORITHMIC PREDICTION OF AGREEMENT
AGREE/DISAGREE/NEITHER
LEXICALuni/bi/trigams
TFIDF
POSraw tags
combo lexical
SENTIMENTcongressional !oor
rotten tomatoesLIWC
SEMANTICsim to post
ESA
NAMED ENTITYorganizations
people
Algorithmic prediction:Lexical features
This feels like an echo chamber within an echo chamber!
Algorithmic prediction:Lexical features
This feels like an echo chamber within an echo chamber!
Algorithmic prediction:POS features
This feels like an echo chamber within an echo chamber!
DT VBZ IN DT JJ NN
IN DT JJ NN
Algorithmic prediction:Semantic features
Cosine similarity to post
WordNet similarity to post
Explicit Semantic Analysis
Algorithmic prediction:Sentiment features
LIWC positive, negative, anger, …
Rotten Tomatoes +/– classifier
Congressional floor +/– classifier
Algorithmic prediction:The actual algorithm
Bagged Complement Naive Bayes
Rennie & Shih. Proc. ICML, 2003.
AGREE/DISAGREE/NEITHER
LEXICALuni/bi/trigams
TFIDF
POSraw tags
combo lexical
SENTIMENTcongressional !oor
rotten tomatoesLIWC
SEMANTICsim to post
ESA
NAMED ENTITYorganizations
people
bagged comp. naive bayes
Learning an NLP-based model of commenter agreement
67.4%
χ2(1, N=196) = 7.6p = 0.006
baseline
model
49.4%
Model accuracy
Rotten Tomatoes classifier: 90%Congressional floor classifier: 71%
LIWC pos. emotion words agree
LIWC affect words agree
exclamations agree
adjectives agree
@ neither
ellipsis !disagree
great agree
is tech blog neither
cosine similarity to post !disagree
great [noun] agree
personal pronouns !disagree
present tense verbs neither
[prepos] [poss pronoun] agree
tf-idf dot product with post !neither
coordinating conjunctions agree
Features + Info Gain
0.079
0.049
0.043
0.041
0.041
0.038
0.035
0.034
0.034
0.03
0.028
0.026
0.026
0.026
0.026
Blogs are echo chambers. 77.9% of opinionated commenters agree with the blog author.
An algorithmic approach could help. Consider an echo index.
Eric Gilbert | Tony Bergstrom | Karrie KarahaliosUniversity of Illinois at Urbana-Champaign
http://social.cs.uiuc.edu/echo.zipall data & code