Unfolding the dimensionality structure of social networks in ideological embeddings

Traditionally, public opinion on different issues of public debate has been studied through polls and surveys. Recent advancements in network ideological scaling methods, however, have shown that digital behavioral traces in social media platforms can be used to mine opinions at a massive scale. This has yet to be shown to work beyond one-dimensional opinion scales, which are best suited for two-party systems and binary social divides such as those observed in the US. In this article, we use multidimensional ideological scaling for coupled with referential attitudinal data for some nodes. We show that opinions can be mined in a multitude of issues: from social networks, embedding them in ideological spaces where dimensions stand for indicators of positive and negative opinions, towards issues of public debate. This method does not require text analysis and is thus language independent. We illustrate this approach on the Twitter follower network of French users leveraging political survey data.

[1]  J. Lo,et al.  Fast Estimation of Ideal Points with Massive Data , 2016, American Political Science Review.

[2]  W. Lowe,et al.  Understanding Wordscores , 2008, Political Analysis.

[3]  Tim Groseclose,et al.  A Measure of Media Bias , 2005 .

[4]  K. T. Poole,et al.  A Spatial Model for Legislative Roll Call Analysis , 1985 .

[5]  Giancarlo Ragozini,et al.  On the use of Multiple Correspondence Analysis to visually explore affiliation networks , 2014, Soc. Networks.

[6]  Political ideology: why the American common man believes what he does , 1964 .

[7]  Ryan Bakker,et al.  Complexity in the European party space: Exploring dimensionality with experts , 2012 .

[8]  N. Sauger,et al.  Economic internationalization and the decline of the left–right dimension , 2019, Party Politics.

[9]  H. McClosky.  Conservatism and Personality , 1958, American Political Science Review.

[10]  M. Greenacre.  Correspondence analysis in practice , 1993 .

[11]  Jean-Philippe Cointet,et al.  Your most telling friends: Propagating latent ideological features on Twitter using neighborhood coherence , 2020, 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[12]  Robert M. Bond,et al.  Quantifying Social Media’s Political Space: Estimating Ideology from Publicly Revealed Preferences on Facebook , 2015, American Political Science Review.

[13]  Jean-Philippe Cointet,et al.  Auditing the Effect of Social Network Recommendations on Polarization in Geometrical Ideological Spaces , 2021, RecSys.

[14]  P. Converse.  The Nature of Belief Systems in Mass Publics , 2004 .

[15]  E. Gallic,et al.  Recovering the French Party Space from Twitter Data , 2015 .

[16]  Angus Campbell,et al.  The American voter , 1960 .

[17]  Christopher Cochrane,et al.  Word Embeddings for the Analysis of Ideological Placement in Parliamentary Corpora , 2019, Political Analysis.

[18]  I. Ajzen,et al.  The Influence of Attitudes on Behavior , 2005 .

[19]  I. Ajzen.  Attitude structure and behavior. , 1989 .

[20]  Preslav Nakov,et al.  Predicting the Topical Stance and Political Leaning of Media using Tweets , 2020, ACL.

[21]  Daryl J. Bem,et al.  Beliefs Attitudes and Human Affairs , 1970 .

[22]  J. Douglas Carroll,et al.  An equivalence relation between correspondence analysis and classical metric multidimensional scaling for the recovery of Euclidean distances , 1997 .

[23]  Gérard Roland,et al.  Dimensions of politics in the European Parliament , 2006 .

[24]  Pablo Barberá.  Birds of the Same Feather Tweet Together: Bayesian Ideal Point Estimation Using Twitter Data , 2015, Political Analysis.

[25]  T. Adorno.  The Authoritarian Personality , 1950 .

[26]  Pablo Barberá,et al.  Understanding the Political Representativeness of Twitter Users , 2015 .

[27]  Igor M. Sokolov,et al.  Modeling echo chambers and polarization dynamics in social networks , 2019, Physical review letters.

[28]  Kenneth Benoit,et al.  The dimensionality of political space: Epistemological and methodological considerations , 2012 .

[29]  John M. Roberts.  Correspondence analysis of two-mode network data , 2000, Soc. Networks.

[30]  John H. Aldrich,et al.  The Use of the Left-Right Scale in Individual's Voting Decisions , 2010 .

[31]  T. V. Dijk,et al.  Ideology: A Multidisciplinary Approach , 1998 .

[32]  Matt Taddy,et al.  Text As Data , 2017, Journal of Economic Literature.