The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index; none of the 10 sources its claims cite is checked for support yet.
Political Polarization on Twitter
Open accessAbstract
In this study we investigate how social media shape the networked public sphere and facilitate communication between communities with different political orientations. We examine two networks of political communication on Twitter, comprised of more than 250,000 tweets from the six weeks leading up to the 2010 U.S. congressional midterm elections. Using a combination of network clustering algorithms and manually-annotated data we demonstrate that the network of political retweets exhibits a highly segregated partisan structure, with extremely limited connectivity between left- and right-leaning users. Surprisingly this is not the case for the user-to-user mention network, which is dominated by a single politically heterogeneous cluster of users in which ideologically-opposed individuals interact at a much higher rate compared to the network of retweets. To explain the distinct topologies of the retweet and mention networks we conjecture that politically motivated individuals provoke interaction by injecting partisan content into information streams whose primary audience consists of ideologically-opposed users. We conclude with statistical evidence in support of this hypothesis.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
Conover et al. analyze political communication on Twitter during the six weeks before the 2010 U.S. midterm elections, using retweet and mention networks built from 252,300 politically relevant tweets. They find that the retweet network is highly segregated along partisan lines, while the mention network is dominated by a single politically heterogeneous cluster, with cross-ideological interaction linked to hashtag content injection.
Key findings
- The retweet network is highly polarized: its modularity is 0.48 versus 0.17 for the mention network, and its modularity z-score against degree-preserving shuffled graphs is 11.02 versus 2.06 for mentions. In the retweet network, cluster A is 93.4% right-leaning and cluster B is 80.1% left-leaning.
- The mention network is politically heterogeneous: it is dominated by a single cluster accounting for more than 97% of users, and cross-ideological links are much more common than in retweets. Observed/expected link ratios for cross-ideological interaction are 0.68 (Left→Right) and 0.77 (Right→Left) in mentions, versus 0.05 and 0.03 in retweets.
- Manual annotation found most politically active users express a political identity: both annotators could not determine identity for only 8% of users, and more than 75% had unambiguous political valences when requiring both annotators to agree. Cohen’s Kappa was 0.80 for left and 0.82 for right, but only 0.42 for undecidable.
- Hashtag content injection helps explain the difference: users with neutral or mixed-valence hashtags receive and produce more inter-ideological mentions, and nearly 30% of tweets in the #p2 search feed originated from right-leaning users. Example valences include #tcot = 0.384 and #p2 = -0.605.
Methods
- Data were collected from Twitter’s gardenhose API between September 14 and November 1, 2010, observing approximately 355 million tweets. Political content was identified using seed hashtags #p2 and #tcot, a Jaccard similarity threshold of 0.005, 66 unique hashtags, and exclusion of 11 ambiguous hashtags, yielding 252,300 politically relevant tweets from more than 45,000 users.
- The authors constructed retweet and mention networks. The retweet network had 23,766 non-isolated nodes out of 45,365 total, with an 18,470-node largest connected component; the mention network had 10,142 non-isolated nodes out of 17,752 total, with a 7,175-node largest component. Analyses focused on the largest connected components.
- Community detection used label propagation seeded by leading-eigenvector modularity maximization for two communities, run 100 times and compared with Adjusted Rand Index. The authors compared observed modularity to 1,000 degree-preserving shuffled graphs, manually annotated 1,000 random users with a non-author judge on 200, and analyzed observed versus expected cross-ideological links and hashtag valence.
Limitations
- The paper states that direct modularity comparison is problematic because the retweet and mention networks differ in size and connectivity, so it uses shuffled graphs as a baseline; it also notes that the normality assumption for modularity values is false and uses Chebyshev’s inequality instead. It further states that cross-ideological interactions are “almost certainly not a panacea” and may reinforce polarization, and calls for further sentiment analysis and follower-network studies.
- Evident from the text: the sample is limited to six weeks before the 2010 U.S. midterm elections and to tweets containing a discovered set of political hashtags, so findings may not generalize to other periods, elections, or political contexts.
- Evident from the text: manual political alignment was based on 1,000 users, the undecidable category had only fair-to-moderate inter-annotator agreement (κ = 0.42), and the mention network is smaller than the retweet network, which may affect comparisons.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
30 Own result · 13 Own interpretation · 5 No full text of the sources · 4 Own method · 3 Sources not found · 3 No basis given
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Figure 2 shows that in the mention network, users placed in the same cluster are not likely to be much more similar to each other than users in different clusters.”
§ Political Polarization on Twitter > 3.2 Content Homogeneity
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We conclude that the community structure found in the retweet network is significantly more segregated than that found in the mention network.”
§ Political Polarization on Twitter > 3.1 Community Structure
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Further, we note that in both mention and retweet networks, one of the clusters is more cohesive than the other -meaning the tag usage within one community is more homogeneous.”
§ Political Polarization on Twitter > 3.2 Content Homogeneity
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“All differences are significant at the 95% confidence level.”
§ Political Polarization on Twitter > 3.2 Content Homogeneity
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Based on this analysis it is clear that a majority of politically active users on Twitter express a political identity in their tweets.”
§ Political Polarization on Twitter > 3.3 Political Polarization
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As a result the average similarity within retweet clusters is higher than across clusters.”
§ Political Polarization on Twitter > 3.2 Content Homogeneity
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Instead we find that it is dominated by a politically heterogeneous cluster accounting for more than 97% of the users”
§ Political Polarization on Twitter > 3.3 Political Polarization
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“messages in this style make up a substantial portion of the results.”
§ Political Polarization on Twitter > 4.2 Content Injection
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A key finding of this study, these results indicate that users contributing to a politically balanced combination of content streams on average receive and produce more inter-ideological communication than those who use mostly partisan hashtags.”
- Also stated in: § 5 Conclusions · hedged
“Specifically, users who apply hashtags with neutral or mixed valence are more likely to engage in communication with opposing communities.”
§ Political Polarization on Twitter > 4.3 Political Valence
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption: Any Twitter user can select arbitrary hashtags to annotate his or her tweets.
- Also stated in: § 5 Conclusions · hedged
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the content is frequently disparaging of the identities and views associated with users across the partisan divide.”
§ Political Polarization on Twitter > 5 Conclusions
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- It may state two separate claims as one. 18
- Probably not a substantial claim. 10
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We observe that the retweet and mention networks exhibit very similar scale-free topology (power-law degree distribution not shown), with a number of users receiving or spreading a huge amount of information.”
§ Political Polarization on Twitter > 2.3 Political Communication Networks
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Using a combination of network clustering algorithms and manually-annotated data we demonstrate that the network of political retweets exhibits a highly segregated partisan structure, with extremely limited connectivity between left-and right-leaning users.”
- Also stated in: § 1 Introduction · boosted
“We demonstrate that the retweet network exhibits a highly modular structure, segregating users into two homogenous communities corresponding to the political left and right.”
- Also stated in: § 3.1 Community Structure · plain
“In summary, the retweet network contains two clusters of users who preferentially propagate content within their own communities.”
§ Political Polarization on Twitter > Abstract
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Also stated in: § 1 Introduction · boosted
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“On the other hand, in the retweet network, users in cluster A are more likely to have very similar profiles than users in cluster B, and users in different clusters are the least similar to each other.”
§ Political Polarization on Twitter > 3.2 Content Homogeneity
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The retweet network exhibits two distinct communities of users, while the mention network is dominated by a single massive cluster of interconnected users.”
- Also stated in: § 3.1 Community Structure · plain
“Figure 1 shows the retweet and mention networks, laid out using a force-directed layout algorithm (Fruchterman and Reingold 1991), with node colors determined by the assigned communities.”
§ Political Polarization on Twitter > 3.1 Community Structure
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Also stated in: § 3.1 Community Structure · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Surprisingly this is not the case for the user-to-user mention network, which is dominated by a single politically heterogeneous cluster of users in which ideologically-opposed individuals interact at a much higher rate compared to the network of retweets.”
- Also stated in: § 1 Introduction · plain
“In contrast, we find that the mention network does not exhibit this kind of political segregation, resulting in users being exposed to individuals and information they would not have been likely to choose in advance.”
- Also stated in: § 1 Introduction · plain
“These data also show the mention network to be politically heterogeneous, with users of opposing political views interacting at a much higher rate than in the retweet network”
§ Political Polarization on Twitter > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Also stated in: § 1 Introduction · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Manual classification of Twitter users by political alignment, demonstrating that the retweet network clusters correspond to the political left and right.”
- Also stated in: § 3 Cluster Analysis · boosted
“by manually annotating users, we show that the retweet network is polarized on a partisan basis, while the mention network is much more politically heterogeneous.”
§ Political Polarization on Twitter > 1 Introduction
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Also stated in: § 3 Cluster Analysis · boosted
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The modularity induced by the communities in the retweet and mention networks have values of 0.48 and 0.17, respectively.”
§ Political Polarization on Twitter > 3.1 Community Structure
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“nearly 30% of the tweets in the #p2 search feed would originate from right-leaning users.”
§ Political Polarization on Twitter > 4.2 Content Injection
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Increasing the number of target communities in the mention network does not reveal a more fine-grained ideological structure, but instead results in smaller yet politically heterogeneous clusters.”
§ Political Polarization on Twitter > 3.3 Political Polarization
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“While we know for certain that ideologically-opposed users interact with one another, either through mentions or content injection, they very rarely share information from across the divide with other members of their community.”
§ Political Polarization on Twitter > 5 Conclusions
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“These two means of communication -retweets and mentions-serve distinct and complementary purposes, together acting as the primary mechanisms for explicit, public user-user interaction on Twitter.”
§ Political Polarization on Twitter > 2.1 The Twitter Platform
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Mentions function differently, allowing someone to address a specific user directly through the public feed, or, to a lesser extent, refer to an individual in the third person (Honeycutt and Herring 2008).”
§ Political Polarization on Twitter > 2.1 The Twitter Platform
What the sources say
- Not matchedcites Honeycutt and Herring 2008
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Not matched
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“In line with the standards of the field, we had a non-author judge with a broad knowledge of politics annotate 200 random users from the set of 1,000 to establish the reproducibility of this annotation scheme.”
§ Political Polarization on Twitter > 3.3 Political Polarization
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
In the paper
“For agreement between the 'left' and 'right' categories we report κ = 0.80 and κ = 0.82 respectively, both of which fall in the "nearly perfect agreement" range (Landis and Koch 1977).”
§ Political Polarization on Twitter > 3.3 Political Polarization
What the sources say
- Not checked — no full text of the sourcecites Landis and Koch 1977 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Retweets act as a form of endorsement, allowing individuals to rebroadcast content generated by other users, thereby raising the content's visibility (boyd, Golder, and Lotan 2008).”
§ Political Polarization on Twitter > 2.1 The Twitter Platform
What the sources say
- Not matchedcites boyd, Golder, and Lotan 2008
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Not matched
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Such a high agreement suggests that the clusters are consistent, and therefore we avoid resorting to consensus clustering for simplicity.”
§ Political Polarization on Twitter > 3.1 Community Structure
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We argue that this process results in users being exposed to content they are not likely to rebroadcast, but to which they may respond using mentions, and provide statistical evidence in support of this hypothesis.”
§ Political Polarization on Twitter > 1 Introduction
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: Each hashtag identifies a stream of content, with users' tag choices denoting participation in different information channels.
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“Adamic and Glance (2005) famously demonstrated that political blogs preferentially link to other blogs of the same political ideology, a finding supported by the work of Hargittai, Gallo, and Kane (2007).”
§ Political Polarization on Twitter > 1 Introduction
What the sources say
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Consumers of online political information tend to behave similarly, choosing to read blogs that share their political beliefs, with 26% more users doing so in 2008than 2004(Pew Internet and American Life Project 2008).”
§ Political Polarization on Twitter > 1 Introduction
What the sources say
- Not matchedcites Pew Internet and American Life Project 2008
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“Despite this, some empirical evidence suggests that politically active web users tend to organize into insular, homogenous communities segregated along partisan lines.”
§ Political Polarization on Twitter > 1 Introduction
What the sources say
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“For the undecidable category we found "fair to moderate" agreement (κ = 0.42), indicating that there are users for whom a political identity might be discernible in the context of specific domain knowledge.”
§ Political Polarization on Twitter > 3.3 Political Polarization
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Many messages contain sentiments more extreme than you would expect to encounter in face-to-face interactions”
§ Political Polarization on Twitter > 5 Conclusions
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We propose that when a user is exposed to ideologically opposed content in this way, she will be unlikely to rebroadcast it, but may choose to respond directly to the originator in the form of a mention.”
§ Political Polarization on Twitter > 4.2 Content Injection
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
- Rests on an assumption: Any Twitter user can select arbitrary hashtags to annotate his or her tweets.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“and ostensibly serves as a place where progressives can once again be exposed only to content aligned with their views.”
§ Political Polarization on Twitter > 4.2 Content Injection
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
- Rests on an assumption: Any Twitter user can select arbitrary hashtags to annotate his or her tweets.
The paper relies on this without support.
When politically active individuals can avoid people and information they would not have chosen in advance, their opinions are likely to become increasingly extreme as a result of being exposed to more homogeneous viewpoints and fewer credible opposing opinions.
“The concern is that when politically active individuals can avoid people and information they would not have chosen in advance, their opinions are likely to become increasingly extreme as a result of being exposed to more homogeneous viewpoints and fewer credible opposing opinions.”
The paper relies on this without support.
A deliberative democracy relies on a broadly informed public and a healthy ecosystem of competing ideas.
“A deliberative democracy relies on a broadly informed public and a healthy ecosystem of competing ideas.”
The paper relies on this without support.
Each hashtag identifies a stream of content, with users' tag choices denoting participation in different information channels.
“Each hashtag identifies a stream of content, with users' tag choices denoting participation in different information channels.”
The authors state this as an assumption.
The modularities of shuffled graph cluster assignments are normally distributed.
“This discussion assumes that the modularities of the shuffled graph cluster assignments are distributed normally, which is not true in general.”
The paper relies on this without support.
The partisan nature of U.S. political discourse makes two a natural number of clusters.
“While the partisan nature of U.S. political discourse makes two a natural number of clusters”
The paper relies on this without support.
Any Twitter user can select arbitrary hashtags to annotate his or her tweets.
“Any Twitter user can select arbitrary hashtags to annotate his or her tweets.”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Political Polarization on Twitter > 2.1 The Twitter Platform
“between September 14th and November 1st, 2010”
§ Political Polarization on Twitter > 2.1 The Twitter Platform
“During the six weeks of data collection”
Citations
Cites
The Measurement of Observer Agreement for Categorical Data
Landis, J. R., & Koch, G. G. (1977) · Biometrics · doi:10.2307/2529310 · Cited by 81,148 · cited 2×
“For agreement between the 'left' and 'right' categories we report κ = 0.80 and κ = 0.82 respectively, both of which fall in the " nearly perfect agreement " range (Landis and Koch 1977).”
BackgroundInfluentialContent Analysis: An Introduction to its Methodology.
Shelley, M., & Krippendorff, K. (1984) · Journal of the American Statistical Association · doi:10.2307/2288384 · Cited by 24,346
Finding and evaluating community structure in networks
Newman, M. E. J., & Girvan, M. (2004) · Physical Review E · doi:10.1103/physreve.69.026113 · Cited by 13,931 · cited 2×
“Modularity (Newman and Girvan 2004) resulting from the cluster assignments offers a first measure of segregation , and reinforces the qualitative finding above.”
ResultHubert, L., & Arabie, P. (1985) · Journal of Classification · doi:10.1007/bf01908075 · Cited by 8,219
Graph drawing by force‐directed placement
Fruchterman, T. M. J., & Reingold, E. M. (1991) · Software: Practice and Experience · doi:10.1002/spe.4380211102 · Cited by 6,352 · cited 1×
“Figure 1 shows the retweet and mention networks, laid out using a force-directed layout algorithm (Fruchterman and Reingold 1991), with node colors determined by the assigned communities.”
MethodFinding community structure in networks using the eigenvectors of matrices
Newman, M. E. J. (2006) · Physical Review E · doi:10.1103/physreve.74.036104 · Cited by 4,799 · cited 2×
“To improve its effectiveness and stability , we seeded the algorithm with initial node labels determined by the leading-eigenvector modularity maximization method for two clusters (Newman 2006).”
MethodNear linear time algorithm to detect community structures in large-scale networks
Raghavan, U. N., Albert, R., & Kumara, S. R. T. (2007) · Physical Review E · doi:10.1103/physreve.76.036106 · Cited by 3,535 · cited 1×
“Label propagation (Raghavan, Albert, and Kumara 2007) works by assigning an initial arbitrary cluster membership to each node and then iteratively updating each node's label according to the label that is shared by most of its neighbors.”
BackgroundPredicting Elections with Twitter: What 140 Characters Reveal about Political Sentiment
Tumasjan, A., Sprenger, T. O., Sandner, P., & Welpe, I. M. (2010) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v4i1.14009 · Cited by 2,647 · cited 1×
“Social media play an important role in shaping political discourse in the U.S. and around the world (Bennett 2003; Benkler 2006; Sunstein 2007; Farrell and Drezner 2008; Aday et al. 2010; Tumasjan et al. 2010; O'Connor et al. 2010).”
BackgroundThe political blogosphere and the 2004 U.S. election: divided they blog
Adamic, L. A., & Glance, N. (2005) · Proceedings of the 3rd international workshop on Link discovery · doi:10.1145/1134271.1134277 · Cited by 2,619
Tweet, Tweet, Retweet: Conversational Aspects of Retweeting on Twitter
Boyd, D., Golder, S., & Lotan, G. (2010) · 2010 43rd Hawaii International Conference on System Sciences · doi:10.1109/hicss.2010.412 · Cited by 2,051 · cited 1×
“Retweets act as a form of endorsement, allowing individuals to rebroadcast content generated by other users, thereby raising the content's visibility (boyd, Golder, and Lotan 2008).”
Background
Research works printed but not linked: 1
- Sunstein, C. R. 2007. Republic.com 2.0. Princeton Univer- sity Press.
Cited by
Sorted by citations
Items 301–400 of 631
A structural approach to detecting opinion leaders in Twitter by random matrix theory
Mohammadi, S., Moradi, P., Trufanov, A. I., & Jafari, G. (2023) · Scientific Reports · doi:10.1038/s41598-023-48682-5 · Cited by 6
Right-Wing Twitter Users in France Exhibit Growing Homophily Compared With Left and Center Users
Gurchani, U. (2024) · Social Media + Society · doi:10.1177/20563051241234689 · Cited by 6
“With the advent of new social media tools, recent years have expanded this insight to encompass the recognition that shared behaviors or ideologies also significantly enhance the likelihood of connection (Conover et al., 2011).”
BackgroundSocial Media: An Ill-Defined Phenomenon
White, J., Fu, K., & Benson, B. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39371-6_47 · Cited by 6
Social infomediation of news on Twitter: A French case study
Smyrnaios, N., & Rieder, B. (2013) · NECSUS · doi:10.5117/necsus2013.2.smyr · Cited by 9
Kasmani, M. F., Sabran, R., & Ramle, N. A. (2014) · Asian Social Science · doi:10.5539/ass.v10n18p144 · Cited by 6
“Each hashtag identifies a stream of content and users’ tag choices denote participation in different information channels (Conover et al., 2011).”
BackgroundEcho Chambers vs Opinion Crossroads in News Consumption on Social Media
Dokuka, S., Koltcov, S., Koltsova, O. Y., et al. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-11027-7_2 · Cited by 6
“The hypothesis about the echo chamber effect facilitated by social media is supported in (Adamic & Glance 2005, Conover et al., 2011, Guerra et al., 2013).”
BackgroundTwitter discourse as a lens into politicians' interest in technology and development
Bozarth, L., & Pal, J. (2019) · International Conference on Information and Communication Technologies and Development (ICTD) · doi:10.1145/3287098.3287129 · Cited by 6
“Keywords and/or Cosine similarity measurement based document clustering has been used extensively by many prior works [1, 6, 30] focused on political communication on social media.”
BackgroundThe Alt-Right and Global Information Warfare
Bevensee, E., & Ross, A. R. (2018) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2018.8622270 · Cited by 7
Articulación de la influencia en Twitter ante el anuncio de la Ley del referéndum en Cataluña
Fernández, C. M. M., Grau-Masot, J.-M., & Capdevila, A. (2019) · El Profesional de la Informacion · doi:10.3145/epi.2019.may.20 · Cited by 6
Political Candidates’ Discussions on Twitter During Election Season: A Network Approach
Vergeer, M. (2020) · Springer eBooks · doi:10.1007/978-3-030-41421-4_3 · Cited by 6
Quoting is not Citing: Disentangling Affiliation and Interaction on Twitter
Roth, C., St-Onge, J., & Herms, K. (2022) · Studies in computational intelligence · doi:10.1007/978-3-030-93409-5_58 · Cited by 7
“On Twitter, this dichotomy separates subscriptions (followers) and (dry) retweets, from mentions and replies, whereby the latter are more cross-cutting than the former [8,20].”
BackgroundEmpirical Study of Relationship between Twitter Mood and Stock Market from an Indian Context
Kumar, S., Maskara, S., Chandak, N., & Goswami, S. (2015) · International Journal of Applied Information Systems · doi:10.5120/ijais15-451352 · Cited by 6
Lappeman, J., Goder, A., Naicker, K., et al. (2023) · Journal of Nonprofit & Public Sector Marketing · doi:10.1080/10495142.2023.2178588 · Cited by 6
Borge‐Holthoefer, J., González‐Bailón, S., Rivero, A., & Moreno, Y. (2014) · Lecture notes in social networks · doi:10.1007/978-3-7091-1340-0_9 · Cited by 7
2015 HAZİRAN VE KASIM SEÇİMLERİNDE SİYASAL EĞİLİM: YENİ BİR KAMUOYU ÖLÇÜMLEME ARACI OLARAK TWİTTER
Toker, H., ERDEM, S., & Özşarlak, P. (2017) · Erciyes İletişim Dergisi · doi:10.17680/erciyesakademia.291888 · Cited by 6
Machedon, R., Rand, W. M., & Joshi, Y. V. (2013) · SSRN Electronic Journal · doi:10.2139/ssrn.2244353 · Cited by 6
Trends and topics: Characterizing echo chambers’ topological stability and in-group attitudes
Cau, E., Morini, V., & Rossetti, G. (2024) · PLOS complex systems. · doi:10.1371/journal.pcsy.0000008 · Cited by 9
Unveiling the drivers of active participation in social media discourse
Baqir, A., Chen, Y., Diaz-Diaz, F., Kiyak, S., Louf, T., Morini, V., Pansanella, V., Torricelli, M., & Galeazzi, A. (2025) · Scientific Reports · doi:10.1038/s41598-025-88117-x · Cited by 5
“This methodology aligns with prevailing practices in Twitter analysis research 3,5,75 , as retweets are regarded as endorsements of content.”
Biswas-Chatterjee-Sen kinetic exchange opinion model for two connected groups
Suchecki, K., Biswas, K., Hołyst, J. A., et al. (2025) · Physical review. E · doi:10.1103/l8z9-f4p9 · Cited by 5
Rodríguez, L. T., & Arroyo, A. Z. (2022) · Observatorio (OBS*) · doi:10.15847/obsobs16320222076 · Cited by 6
Albrecht, F., & Walter-Rogg, M. (2023) · Springer eBooks · doi:10.1007/978-3-658-41392-7_11 · Cited by 5
“#schleichdiduoaschloch” Terror, Collective Memory, and Social Media
Tambuscio, M., & Tschiggerl, M. (2023) · Social Media + Society · doi:10.1177/20563051231186365 · Cited by 9
“In our analysis, we used a mixture of qualitative and quantitative methods as a blended reading (Lemke & Wiedemann, 2016, p. 21) and different forms of network analysis (Conover et al., 2011; Newman, 2018; Scott, 2013; Wang et al., 2016).”
MethodTopology modification against membership inference attack in Graph Neural Networks
Guan, F., Zhu, T., Tong, H., & Zhou, W. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112642 · Cited by 5
Zago, G. D. S., & Bastos, M. T. (2013) · Brazilian Journalism Research · doi:10.25200/bjr.v9n1.2013.568 · Cited by 5
Fitriyah, P., Fatoni, A. S., & Nasher, A. (2020) · doi:10.2991/assehr.k.201219.035 · Cited by 5
“and more important here than on other social media platforms [6].”
BackgroundMisinformation, Fake News and Rumor Detection
Arora, N. (2021) · Smart innovation, systems and technologies · doi:10.1007/978-981-16-3398-0_14 · Cited by 7
Guerrero-Solé, F., Capdevila, E. P., Aira, T., et al. (2022) · Revista Mediterránea de Comunicación · doi:10.14198/medcom.19953 · Cited by 5
A novel method detecting controversial interaction in the multiplex social comment network
Li, Z., Zhang, J., Xuan, Q., et al. (2023) · Frontiers in Physics · doi:10.3389/fphy.2022.1107338 · Cited by 5
What to predict from Twitter Data?
Salemdeeb, M., & Sahmoud, S. (2023) · International Conference on Computing and Information Technology (ICCIT) · doi:10.1109/iccit58132.2023.10273883 · Cited by 5
Online Social Behavior Enhanced Detection of Political Stances in Tweets
Peng, X., Zhou, Z., Zhang, C., & Xu, K. (2024) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v18i1.31383 · Cited by 6
“We take into account both posting and retweeting behaviors, as users often retweet messages that align with their ideological preferences (Conover et al. 2011; Wong et al. 2016).”
BackgroundExploring cognitive inertia in opinion dynamics using an activity-driven model
Pranesh, S., & Gupta, S. (2024) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2024.115879 · Cited by 5
Joint Spectral Clustering in Multilayer Degree-Corrected Stochastic Blockmodels
Agterberg, J., Lubberts, Z., & Arroyo, J. (2025) · Journal of the American Statistical Association · doi:10.1080/01621459.2025.2516201 · Cited by 5
“…in a coherent manner that somehow reflects the structure of the network, has become a fundamental tool for the analysis of network data, with many applications in fields such as neuroscience (Sporns and Betzel 2016), biology (Luo et al. 2007), social sciences (Conover et al. 2011), among others.”
Ali, A. C., Yimam, S. M., Ayele, A. A., et al. (2025) · i-com · doi:10.1515/icom-2025-0007 · Cited by 5
“22,23 However,exposuretoopposing viewpointsdoesnot lead to partisansbecominglesscommit-ted to their positions.”
Bodrunova, S. S., Blekanov, I. S., Kukarkin, M., & Zhuravleva, N. N. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01437-7_18 · Cited by 5
Fact-Checking, Fake News, Propaganda, and Media Bias: Truth Seeking in the Post-Truth Era
Nakov, P., & Martino, G. D. S. (2020) · doi:10.18653/v1/2020.emnlp-tutorials.2 · Cited by 7
An analytics approach to health and healthcare in citizen science communications on Twitter
Martínez-Martínez, F., Álvarez, D. R., Martín, E., & Hoppe, H. U. (2023) · Digital Health · doi:10.1177/20552076221145349 · Cited by 5
“24 If a user considers that a piece of information could be relevant to other users, he/she cites then within a tweet to capture their attention.”
BackgroundZhao, W., Walasek, L., & Brown, G. D. A. (2023) · Human Behavior and Emerging Technologies · doi:10.1155/2023/9094933 · Cited by 8
Machine learning-based prediction of Q-voter model in complex networks
Pineda, A. M., Kent, P. R. C., Connaughton, C., & Rodrigues, F. A. (2023) · Journal of Statistical Mechanics Theory and Experiment · doi:10.1088/1742-5468/ad06a6 · Cited by 5
Computational Assessment of Hyperpartisanship in News Titles
Lyu, H., Pan, J., Wang, Z., & Luo, J. (2024) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v18i1.31368 · Cited by 9
Using Twitter to Track Immigration Sentiment During Early Stages of the COVID-19 PandemicPreprint
Rowe, F., Mahony, M., Graells-Garrido, E., Rango, M., & Sievers, N. (2021) · doi:10.31235/osf.io/pc3za · Cited by 5
Investigating Language Use by Polarised Groups on Twitter: A Case Study of the Bushfires
Nasim, M., Sharif, N., Bhandari, P., Weber, D., Wood, M., Falzon, L., & Kashima, Y. (2022) · Australasian Document Computing Symposium · doi:10.1145/3572960.3572979 · Cited by 4
“Indeed, online polarisation is a broad and well-studied topic [9], including in the context of politics [1].”
BackgroundMouvements sociaux sur Twitter et Digital Methods : des données aux analyses
Loubère, L. (2021) · Terminal · doi:10.4000/terminal.7054 · Cited by 4
Zareie, A., & Sakellariou, R. (2023) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3625826 · Cited by 5
“The impact of online social networks on users’ opinion formation has led to an analysis of how controversial debates take place in such networks [9, 21].”
BackgroundIn-party love spreads more efficiently than out-party hate in online communities
Martín-Gutíerrez, S., Robles, J. M., Torcal, M., Losada, J. C., & Benito, R. M. (2024) · Scientific Reports · doi:10.1038/s41598-024-65688-9 · Cited by 9
“Similar observations were made during the 2010 U.S. Congress elections, revealing that retweets were more ideologically polarizing than mentions among regular users 96 .”
ResultYörük, E., Atsızelti, Ş., KINA, M. F., Duruşan, F., Gürerk, O., Yardı, M. C., Hürriyetoğlu, A., Mutlu, O., Etgü, T., Koyuncu, M., et al. (2024) · The Developing Economies · doi:10.1111/deve.12424 · Cited by 4
Martyanov, D. S., Luk'yanova, G. V., & Lagutin, O. (2019) · Communications in computer and information science · doi:10.1007/978-3-030-37858-5_13 · Cited by 4
Nip, J. Y. M., & Cheng, Y. (2022) · Journalism and Media · doi:10.3390/journalmedia3030039 · Cited by 4
Caracterização e Predição de Usuários Tóxicos no Twitter/X durante as Eleições Brasileiras de 2022
Pinto, S. L., Campolina, J. J., Sena, J. P. M., Félix, G., Ferreira, L. N., & Reis, J. C. S. (2024) · Anais do Brazilian Workshop on Social Network Analysis and Mining (BraSNAM) · doi:10.5753/brasnam.2024.2515 · Cited by 7
A Multiple Feature Integration Model to Infer Occupation from Social Media Records
Wang, X., Yu, L., Yao, J., et al. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-41154-0_10 · Cited by 4
“[5] points out that in social network, the mention function(@) often plays a role to connect users having different or even opposed opinions and behaviors, which results in the poor homophily phenomenon in mention network.”
BackgroundORKESTRASI BUZZER MELALUI MEDIA SOSIAL MICROBLOGGING DALAM KAMPANYE PENANGANAN VIRUS COVID-19
Putra, A., & Irwansyah, I. (2020) · Jurnal Riset Komunikasi · doi:10.38194/jurkom.v3i2.151 · Cited by 4
Public opinion formation with the spiral of silence on complex social networks
Takeuchi, D., Tanaka, G., Fujie, R., & Suzuki, H. (2015) · Nonlinear Theory and Its Applications IEICE · doi:10.1587/nolta.6.15 · Cited by 5
“The other is the complex topology of social interaction networks, which is often found in Twitter [19], Facebook [20], social networking sites [7], and other online social networks [21, 22].”
BackgroundModeling User Interest and Community Interest in Microbloggings: An Integrated Approach
Hoang, T.-A. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-18038-0_55 · Cited by 4
Media Partisanship During Election: Indonesian Cases
Maulana, A., & Situngkir, H. (2020) · Studies in computational intelligence · doi:10.1007/978-3-030-65347-7_54 · Cited by 4
The Ocean of Possible Truth. Drivers and Consequences of News Accuracy Judgements OnlinePreprint
von Hohenberg, B. C. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3281038 · Cited by 4
When Groups Fall Apart: Identifying Transnational Polarization with Twitter from the Arab UprisingsPreprint
Kubinec, R., & Owen, J. M. (2018) · SocArXiv (OSF Preprints) · doi:10.31235/osf.io/wykmj · Cited by 4
Keyword Expansion Techniques for Mining Social Movement Data on Social MediaPreprint
Bozarth, L., & Budak, C. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3878554 · Cited by 4
Populismo de extrema derecha y redes sociales en España
Guerrero Solé, F., & Virós-Martín, C. (2023) · doi:10.31009/cr.2023.04 · Cited by 4
Cannabis-Related Political Discourse on Twitter: A Mixed Methods Approach
Athey, N. C. (2024) · Journal of Drug Issues · doi:10.1177/00220426241249091 · Cited by 3
“For instance, Conover et al. (2011) discovered highly segregated Twitter networks, especially along partisan political lines, with limited connectivity between the left (liberal/democratic) and right-(republican/conservative) leaning communities.”
Beyond Boundaries: Capturing Social Segregation on Hypernetworks
Failla, A., Rossetti, G., & Cauteruccio, F. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-78541-2_3 · Cited by 3
Emotionality in Political Social Media Communications: The Moderating Role of Audience Diversity
Fossen, B. L., & Schweidel, D. A. (2025) · Information Systems Research · doi:10.1287/isre.2022.0064 · Cited by 3
Terren, L. (2022) · Communications · doi:10.1515/commun-2021-0108 · Cited by 3
Lopes, A. D. S., & Brotas, A. M. P. (2023) · Research Society and Development · doi:10.33448/rsd-v12i2.40159 · Cited by 4
Societal Implications of Recommendation Systems: A Technical Perspective
Gonçalves-Sá, J., & Pinheiro, F. L. (2023) · Law, governance and technology series · doi:10.1007/978-3-031-41264-6_3 · Cited by 5
Lee, J., Chung, C. J., & Kim, D. (2024) · Social Sciences · doi:10.3390/socsci13020094 · Cited by 4
Dynamic games on arbitrary networks with two types of players
Pei, S., Cressman, R., & Zhang, B. (2024) · Journal of Mathematical Economics · doi:10.1016/j.jmateco.2024.102990 · Cited by 3
Cross-community affinity: A polarization measure for multi-community networks
Nair, S., & Iamnitchi, A. (2024) · Online Social Networks and Media · doi:10.1016/j.osnem.2024.100280 · Cited by 3
Cultural and opinion dynamics in small-world “social” networks
Lee, Y. (2024) · Journal of Mathematical Sociology · doi:10.1080/0022250x.2024.2423941 · Cited by 3
“Liberals and conservatives are strongly segregated and clustered in both in-person and online networks (Conover et al., 2011; Gentzkow & Shapiro, 2011).”
Political Leanings in Web3 Betting: Decoding the Interplay of Political and Profitable Motives
Chen, H., Duan, X., Saddik, A. E., & Cai, W. (2025) · ACM Web Science Conference (WebSci) · doi:10.1145/3717867.3717884 · Cited by 3
“Similarly, Conover et al. [20] demonstrate the potential of aggregated digital foot-prints, such as social media interactions.”
Guo, Q. (2025) · Journal of Documentation · doi:10.1108/jd-09-2024-0211 · Cited by 3
Characterizing the 2016 U.S. Presidential Campaign using Twitter Data
Vegas, I. M. A., Tian, T. M., & Xiong, W. (2016) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2016.071002 · Cited by 3
“congressional midterm elections [16].”
Kessler, G., Focás, B., de Zárate, J. M. O., & Feuerstein, E. (2020) · REVISTA SAAP · doi:10.46468/rsaap.14.2.a3 · Cited by 4
STRUKTURA SLOVENSKE POLITIČNE RAZPRAVE NA TWITTERJU OB VOLITVAH V EVROPSKI PARLAMENT
Jesenšek, L., Verčič, D., & Kronegger, L. (2021) · Teorija in praksa · doi:10.51936/tip.58.1.49-71 · Cited by 3
Counteracting Filter Bubbles with Homophily-Aware Link Recommendations
Warton, R., Volny, C., & Xu, K. S. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-17114-7_15 · Cited by 3
A comparative framework to analyze convergence on Twitter electoral conversations
Cárdenas-Sánchez, D., Sampayo, A. M., Rodríguez-Prieto, M., et al. (2022) · Scientific Reports · doi:10.1038/s41598-022-21861-6 · Cited by 3
Garnier, S., & Moussaïd, M. (2022) · Collective Intelligence · doi:10.1177/26339137221133400 · Cited by 5
“Indeed, recent studies of the political discourse and opinions in several democratic countries have shown a signi fi cant shift towards polarized political alternatives that appear increasingly incompatible with each other in their presentation (B ¨ ottcher and Gersbach, 2020; Conover et al., 2011).”
BackgroundArtificial Intelligence Techniques Used to Extract Relevant Information from Complex Social Networks
Paramés-Estévez, S., Carballosa, A., García-Selfa, D., & Muñuzuri, A. P. (2023) · Entropy · doi:10.3390/e25030507 · Cited by 3
An organizational form framework to measure and interpret online polarization
Phillips, S. C., & Carley, K. M. (2023) · Information Communication & Society · doi:10.1080/1369118x.2023.2240580 · Cited by 3
“…E/I index as a measure of ‘ echo-chamberness ’ or segregation of polarized groups (Bojanowski & Corten, 2014; Krackhardt & Stern, 1988; Uyheng & Carley, 2020) and modularity to measure group structure of communities de fi ned by partisanship (Conover et al., 2011; Garcia et al., 2015; Newman, 2006).”
BackgroundWallaschek, S., Kaushik, K., & Eigmüller, M. (2023) · Journal of Information Technology & Politics · doi:10.1080/19331681.2023.2278539 · Cited by 3
“Retweets connect two users if one rebroadcasts another’s content and thus are responsible for increasing the visibility of actors if they are retweeted by others (Boyd, Golder, & Lotan, 2010; Conover et al., 2021).”
BackgroundPolarizing Topics on Twitter in the 2022 United States Elections
Katalinić, J., Đunđer, I., & Seljan, S. (2023) · Information · doi:10.3390/info14110609 · Cited by 11
“Conover et al. [6] state that the content of political discourse on X remains highly partisan, with many messages containing sentiments more extreme than expected in face-to-face interactions, while the content frequently disparages identities and views associated with users across the partisan…”
BackgroundTolsma, J., & Spierings, N. (2024) · Information, Communication & Society · doi:10.1080/1369118x.2024.2305159 · Cited by 5
“Indeed, existing studies indicate that @-mentions, of our three di ff erent Twitter networks, are used most to hold discussions (e.g., Conover et al., 2021; Del Valle et al., 2022; Jacobs et al., 2020).”
Modeling the Co-evolving Polarization of Opinion and News Propagation Structure in Social Media
Prasetya, H. A., & Murata, T. (2018) · Studies in computational intelligence · doi:10.1007/978-3-030-05414-4_25 · Cited by 4
A Novel Centrality-based Measure for Election Network Analysis
Chakraborty, A., Badyal, N., Sharma, A., et al. (2022) · IEEE Silchar Subsection Conference (SILCON) · doi:10.1109/silcon55242.2022.10028812 · Cited by 3
“Twitter has been widely used as a platform for predicting presidential election campaigns outcomes, user political learning and political orientation of user expressions in various studies [3], [4], [5].”
MethodVisualization of the Public’s Opinion on Politically Influential Tweets
Kim, T., & DiSalvo, C. F. (2021) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v6i4.14359 · Cited by 3
“…and social networks that are politically meaningful; investigating the effects of Twitter on an election (Tumasja 2010), discovering the network segregation according to political orientations (Conover 2011), and computing the political preference of the citizens (Golbeck 2011) to list a few.”
BackgroundOgawa, Y., Yamamoto, H., & Miyata, K. (2014) · Transactions of the Japanese Society for Artificial Intelligence · doi:10.1527/tjsai.29.483 · Cited by 3
The Public’s Perception of Political Parties During the 2014 Québec Election on Twitter
Sanger, W., & Warin, T. (2018) · Canadian Journal of Communication · doi:10.22230/cjc.2018v43n2a3251 · Cited by 3
Profiling Accounts Political Bias on Twitter
Guimar�ães, N., Figueira, Á., & Torgo, L. (2021) · Iberian Conference on Information Systems and Technologies (CISTI) · doi:10.23919/cisti52073.2021.9476652 · Cited by 3
Nuernbergk, C. (2022) · Springer eBooks · doi:10.1007/978-3-658-26233-4_54 · Cited by 3
Alves, D. S. (2015) · RIUnB Institutional Repository (University of Brasília) · doi:10.26512/2015.10.t.19345 · Cited by 3
“Em [57], é discutido como a mídia social molda a esfera pública e facilita (14)http://www.”
BackgroundBerman, R., Melumad, S., Humphrey, C., & Meyer, R. J. (2017) · SSRN Electronic Journal · doi:10.2139/ssrn.2905484 · Cited by 3
Peeking into the other half of the glass : handling polarization in recommender systems.
Badami, M. (2017) · doi:10.18297/etd/2693 · Cited by 3
“[155] showed this fact by employing a combination of network clustering algorithms on the Twitter graph.”
MethodKasahara, I., & Karasawa, M. (2025) · Asian Journal Of Social Psychology · doi:10.1111/ajsp.12677 · Cited by 4
Maulana, H. F., Rando, R., Hastuti, H., Zaitullah, L. O. M., & Ferizka, Z. Z. (2025) · Frontiers in Communication · doi:10.3389/fcomm.2025.1710197 · Cited by 6
“Strategically, communicators should prioritize sustained, cross-platform repetition of a small set of salient cues; consistent exposure strengthens issue centrality and perceived legitimacy (Conover et al., 2021).”
MATRIZes, E., & Schroeder, R. (2018) · Matrizes · doi:10.11606/issn.1982-8160.v12i2p135-163 · Cited by 3
Examining Similar and Ideologically Correlated Imagery in Online Political Communication
Joshi, A., & Buntain, C. (2024) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v18i1.31351 · Cited by 4
“In this context, Zhang and Peng (2022) (Diermeier et al. 2012), news (Messing, Kessel, and Hughes 2017), and social interaction (Conover et al. 2021).”
BackgroundPerera, S., Perera, I., & Ahangama, S. (2023) · International Conference on Advanced Research in Computing (ICARC) · doi:10.1109/icarc57651.2023.10145632 · Cited by 2
“Therefore, it is easy to identify two separate networks consisting of retweets and mentions [8].”
BackgroundShora, S. R., Arya, A., & Pal, J. (2023) · Global Policy · doi:10.1111/1758-5899.13241 · Cited by 2
Biased or Debiased: Polarization-aware Embedding Learning from Social Media Knowledge Graph
Zhang, Y., Hara, T., & Yao, L. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191992 · Cited by 2
“Sometimes the bias in social media can be also referred to as polarization , particularly in the context of political settings [22], [23].”
BackgroundAnimalization of Kurds in Turkish-Speaking Social Media
Tutkal, S. (2024) · Nationalities Papers · doi:10.1017/nps.2023.32
“Retweet networks are known to disclose political alignments in Twitter data sets when community detection is applied to them (Conover et al. 2011; Ozer, Kim, and Davulcu 2016).”
Gaining a better understanding of online polarization by approaching it as a dynamic process
Treuillier, C., Castagnos, S., Lagier, C., & Brun, A. (2024) · Scientific Reports · doi:10.1038/s41598-024-58915-w · Cited by 5
“In this new informational context, many works attempt to model [13, 14, 15], measure [16, 17, 18, 19], and identify [20] polarization.”
BackgroundEmociones y liderazgos políticos en las elecciones al Parlamento de Andalucía de 2022 en X
Zarauza-Castro, J., & Muros, S. M. (2024) · Universitas · doi:10.17163/uni.n41.2024.08 · Cited by 2
Metadata
- Authors
- Conover, M., Ratkiewicz, J., Francisco, M., Goncalves, B., Menczer, F., & Flammini, A.
- Affiliations
- Indiana University (US)
- Venue
- Proceedings of the International AAAI Conference on Web and Social Media
- Published
- 2021-08-03
- Volume
- 5
- Issue
- 1
- Pages
- 89-96
- ISSN
- 2162-3449 (ISSN-L)
- 2334-0770
- OpenAlex
- W4312820073
- Semantic Scholar
- 9a7ae269358c6366cc46dc924d63b47ba405d082
- Cited by
- 626
- References
- 21
- Citations by year
- 2026: 34 · 2025: 66 · 2024: 86 · 2023: 82 · 2022: 65 · 2021: 62
- FWCI
- 107.66
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Proceedings of the International AAAI Conference on Web and Social Media (publishedVersion)
- AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
- Topics
- Social Sciences › Communication › Social Media and Politics
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Complex Network Analysis Techniques
- Keywords
- political polarization, Twitter, retweets, mentions, social network topology, 2010 midterm elections, political communication, information dissemination, network clustering
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-13, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-13 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
