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

Zamal, Faiyaz Al; Liu, Wendy; Ruths, Derek

doi:10.1609/icwsm.v6i1.14340

Cited by 97 publications

(51 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…including gender, age, education, political orientation, and even coffee preferences (Zamal, Liu, and Ruths 2012;Conover et al 2011b;2011a;Rao and Yarowsky 2010;Pennacchiotti and Popescu 2011;Wong et al 2013;Liu and Ruths 2013;Golbeck and Hansen 2011;Burger, Henderson, and Zarrella 2011). In general, inference algorithms have achieved accuracy rates in the range of 85%, but have struggled to improve beyond this point.…”

Section: Introductionmentioning

confidence: 99%

Classifying Political Orientation on Twitter: It’s Not Easy!

Cohen

Ruths

2021

ICWSM

View full text Add to dashboard Cite

Numerous papers have reported great success at inferring the political orientation of Twitter users. This paper has some unfortunate news to deliver: while past work has been sound and often methodologically novel, we have discovered that reported accuracies have been systemically overoptimistic due to the way in which validation datasets have been collected, reporting accuracy levels nearly 30% higher than can be expected in populations of general Twitter users. Using careful and novel data collection and annotation techniques, we collected three different sets of Twitter users, each characterizing a different degree of political engagement on Twitter - from politicians (highly politically vocal) to "normal" users (those who rarely discuss politics). Applying standard techniques for inferring political orientation, we show that methods which previously reported greater than 90% inference accuracy, actually achieve barely 65% accuracy on normal users. We also show that classifiers cannot be used to classify users outside the narrow range of political orientation on which they were trained. While a sobering finding, our results quantify and call attention to overlooked problems in the latent attribute inference literature that, no doubt, extend beyond political orientation inference: the way in which datasets are assembled and the transferability of classifiers.

show abstract

Section: Introductionmentioning

confidence: 99%

Classifying Political Orientation on Twitter: It’s Not Easy!

Cohen

Ruths

2021

ICWSM

View full text Add to dashboard Cite

show abstract

“…Distinguishing account types can be viewed as a type of latent attribute inference, which aims to infer various properties of online accounts. While only recently has latent attribute inference work begun to examine the organizationperson distinction, much work has been done on other specific 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). Our work is complementary and may offer an important benefit by removing noise from organizational accounts which do not have human attributes.…”

Section: Related Workmentioning

confidence: 96%

Organizations Are Users Too: Characterizing and Detecting the Presence of Organizations on Twitter

McCorriston

Jurgens

Ruths

2021

ICWSM

View full text Add to dashboard Cite

Much work on the demographics of social media platforms such as Twitter has focused on the properties of individuals, such as gender or age. However, because credible detectors for organization accounts do not exist, these and future large-scale studies of human behavior on social media can be contaminated by the presence of accounts belonging to organizations. We analyze organizations on Twitter to assess their distinct behavioral characteristics and determine what types of organizations are active. We first create a dataset of manually classified accounts from a representative sample of Twitter and then introduce a classifier to distinguish between organizational and personal accounts. In addition, we find that although organizations make up less than 10% of the accounts, they are significantly more connected, with an order of magnitude more friends and followers.

show abstract

“…In recent years many scientists have tried to analyse the demographic breakdown of a population of Twitter users [10][11][12][13][14]. Recent advanced algorithms that can infer the gender category from text features e.g.…”

Section: Related Workmentioning

confidence: 99%

Name based Gender Identification using Machine Learning and Deep Learning Models

Ghosh¹

2022

Preprint

View full text Add to dashboard Cite

<p>Name of a person reflects a lot about his origin, gender and more. Naming is a fragment of language and can be an identifier as it contains patterns that could be learned in order to classify individual’s gender based on their names (first name and middle name). In this paper a multi-national, multi-ethnicity and multi-language names (first name) based classification or guessing of gender is per-formed by popular Machine Learning and Deep Learning models. Recent advancements of various Artificial Intelligence inspired algorithms offer various options for text classification. This paper investigates first name based gender identification on a dataset of 84,899 first names and middle name initials with gender labels. The algorithms tested on this task are Support Vector Classifications (linear and non-linear), Nearest Neighbors, Decision Tree, Random Forest, Multi-layer Perceptron, Long Short-Term Memory (LSTM), Bidirectional LSTM, Convolutional Neural Network and a simple embedding based deep learning model (SimpleText). Among the models the significant results out of this study is that linear model (94.62%) performs equivalent with the complex machine learning models and the simple embedding based deep learning network SimpleText outperforms (94.67%) all the models, even the other Recurrent and Convolutional networks </p>

show abstract

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

Cited by 97 publications

References 12 publications

Classifying Political Orientation on Twitter: It’s Not Easy!

Classifying Political Orientation on Twitter: It’s Not Easy!

Organizations Are Users Too: Characterizing and Detecting the Presence of Organizations on Twitter

Name based Gender Identification using Machine Learning and Deep Learning Models

Contact Info

Product

Resources

About