Homophily and Latent Attribute Inference: Inferring Latent Attributes of Twitter Users from Neighbors

By Faiyaz Al Zamal, Wendy Liu, Derek Ruths. 2012

371 citations recorded by the source corpus.

In this paper, we extend existing work on latent attribute inference by leveraging the principle of homophily: we evaluate the inference accuracy gained by augmenting the user features with features derived from the Twitter profiles and postings of her friends. We consider three attributes which have varying degrees of assortativity: gender, age, and political affiliation. Our approach yields a significant and robust increase in accuracy for both age and political affiliation, indicating that our approach boosts performance for attributes with moderate to high assortativity. Furthermore, different neighborhood subsets yielded optimal performance for different attributes, suggesting that different subsamples of the user's neighborhood characterize different aspects of the user herself. Finally, inferences using only the features of a user's neighbors outperformed those based on the user's features alone. This suggests that the neighborhood context alone carries substantial information about the user.

Subfields: Artificial Intelligence, General Social Sciences

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In General Social Sciences

Citations in the corpus

"How Old Do You Think I Am?" A Study of Language and Age in Twitter (2013, methodology): “Some approaches used lists of male and female names, for example obtained using Facebook (Fink, Kopecky, and Morawski 2012) or from the US social security department (Zamal, Liu, and Ruths 2012; Bamman, Eisenstein, and Schnoebelen 2012).”
Predicting Twitter User Demographics from Names Alone (2018, methodology): “Most methods rely on content authored by the user, where words or phrases are strongly associated with speciﬁc demographic traits (Al Zamal et al., 2012).”
Organizations Are Users Too: Characterizing and Detecting the Presence of Organizations on Twitter (2015, background): “…aspects such as political affiliation (Cohen and Ruths 2013), gender (Ciot, Sonderegger, and Ruths 2013; Alowibdi , Buy, and Yu 2013), age (Nguyen, Smith, and Rosé 2011; Nguyen et al. 2013), location (Jurgens 2013), or combinations thereof (Zamal, Liu, and Ruths 2012; Li, Ritter, and Hovy 2014).”
You Are Who You Know and How You Behave: Attribute Inference Attacks via Users' Social Friends and Behaviors (2016, methodology): “[45] used a user’s tweets and her neighbors’ tweets to infer attributes.”
Computational Sociolinguistics: A Survey (2016, methodology): “[276] classified Twitter users into 18-23 and 25-30.”
Beyond Binary Labels: Political Ideology Prediction of Twitter Users (2017, background): “These include users who explicitly state their political orientation on user lists of party supporters (Zamal et al., 2012; Pennacchiotti and Popescu, 2011), supporting par-”
AttriInfer: Inferring User Attributes in Online Social Networks Using Markov Random Fields (2017, background): “Zamal et al. [33] used a user’s tweets and her neighbors’ tweets to infer attributes.”
Studying User Income through Language, Behaviour and Affect in Social Media (2015, methodology): “To ensure the quality of subjective annotations we tested the models trained on crowd-sourced labels on publicly available data from [11, 30] for classifying gender and political orientation.”
Inferring international and internal migration patterns from Twitter data (2014, methodology): “Other text- and networkbased methods to infer the age and gender could also be applied [25].”
Collective aspects of privacy in the Twitter social network (2018, methodology): “For example, Twitter data can be used to predict user locations [13, 14] as well as gender, age, and political orientation of users [15].”
Quantifying Political Leaning from Tweets and Retweets (2013, background): “Machine learning techniques have been proposed to classify Twitter users using e.g., linguistic content, mention/retweet behavior and social network structure (Boutet, Kim, and Yoneki 2012; Al Zamal, Liu, and Ruths 2012; Pennacchiotti and Popescu 2011).”
Gender Inference of Twitter Users in Non-English Contexts (2013, methodology): “(Rao et al., 2010; Pennacchiotti and Popescu, 2011; Burger et al., 2011; Zamal et al., 2012), though boosted decision trees and latent dirichlet allocation systems have also been evaluated, e.”
Online and Social Media Data As an Imperfect Continuous Panel Survey (2016, background): “[43] documents the demographic skew on Twitter along with other studies that focus on inferring unknown demographics and attributes of social media users [44,45,46,47], but do little in joining this information with activity and content.”