Inferring personal economic status from social network location

Luo, Shaojun; Morone, Flaviano; Sarraute, Carlos; Travizano, Matías; Makse, Hernán A.

doi:10.1038/ncomms15227

Cited by 70 publications

(46 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There is enough evidence to justify the significant relationship between mobile phone usage and many socioeconomic factors such as demographic statistics and education levels (Frias-Martinez and Virseda, 2012). In particular, previous research showed that an individual's wealth can be predicted at high accuracy from features of personal social network retrieved from his/her mobile phone calls and SMS metadata (Luo et al, 2017). Therefore, mobile phone metadata provides an alternative to collecting localized and timely information and again, serves as a complement of the traditional methods such as household survey data and national censuses, often at a relatively lower data acquisition cost.…”

Section: Mobile Phone Calls and Sms Datamentioning

confidence: 99%

Household wealth proxies for socio-economic inequality policy studies in China

et al. 2020

View full text Add to dashboard Cite

In China, one percent of the richest population holds more than one-third of the wealth, while the poorest 25% shares no more than two percent of the total. The country’s rapid economic development has resulted in increasing socio-economic disparities, and a rapidly deteriorating environment. This puts the Chinese citizens, especially the most vulnerable and deprived socio-economic status (SES) groups, at high risks of environmental inequality (EI). In most SES-based EI studies conducted in China, household wealth has often been overlooked, though it potentially serves a good economic indicator to capture the socio-economic effect of environmental change in China. Nevertheless, existing SES databases in China are of low spatial resolution and are insufficient to support fine-grained EI studies at the intra-city level in China. The core research challenge is to develop a representative household wealth proxy in high-spatial resolution for China. This study highlights the research gaps and proposes a new household wealth proxy, which integrates both fine-grained data/features such as daytime satellite imagery and easily accessible wealth indicators such as house prices. We also capitalize on everyday economic activity data retrieved from personal mobile phones and online transaction/social platforms in the composition of our wealth proxy to achieve a higher accuracy in estimating household wealth at fine-grained resolution via machine learning. Finally, we summarize the challenges in improving both the quality and the availability of Chinese socio-economic datasets, while protecting personal privacy and information security during the data collection process for household wealth proxy development in China.

show abstract

Section: Mobile Phone Calls and Sms Datamentioning

confidence: 99%

Household wealth proxies for socio-economic inequality policy studies in China

et al. 2020

View full text Add to dashboard Cite

show abstract

“…There is a growing effort in the field to combine online behavioral data with census records, and expert annotated information to infer social attributes of users of online services. The predicted attributes range from easily assessable individual characteristics such as age [15], or occupation [11,[16][17][18], to more complex psychological and sociological traits like political affiliation [19], personality [20], or SES [11,21].…”

Section: Related Workmentioning

confidence: 99%

Optimal Proxy Selection for Socioeconomic Status Inference on Twitter

2019

View full text Add to dashboard Cite

Individual socioeconomic status inference from online traces is a remarkably difficult task. While current methods commonly train predictive models on incomplete data by appending socioeconomic information of residential areas or professional occupation profiles, little attention has been paid to how well this information serves as a proxy for the individual demographic trait of interest when fed to a learning model. Here we address this question by proposing three different data collection and combination methods to first estimate and, in turn, infer the socioeconomic status of French Twitter users from their online semantics. We assess the validity of each proxy measure by analyzing the performance of our prediction pipeline when trained on these datasets. Despite having to rely on different user sets, we find that training our model on professional occupation provides better predictive performance than open census data or remote sensed expert annotation of habitual environments. Furthermore, we release the tools we developed in the hope it will provide a generalizable framework to estimate socioeconomic status of large numbers of Twitter users as well as contribute to the scientific discussion on social stratification and inequalities.

show abstract

“…There is a growing effort in the field to combine online behavioral data with census records, and expert annotated information to infer social attributes of users of online services. The predicted attributes range from easily assessable individual characteristics such as age [18], or occupation [20], [22], [41], [42] to more complex psychological and sociological traits like political affiliation [46], personality [44], or SES [35], [42].…”

Section: Related Workmentioning

confidence: 99%

Location, Occupation, and Semantics Based Socioeconomic Status Inference on Twitter

Abitbol

Karsai

Fleury

2018

2018 IEEE International Conference on Data Mining Workshops (ICDMW)

View full text Add to dashboard Cite

The socioeconomic status of people depends on a combination of individual characteristics and environmental variables, thus its inference from online behavioral data is a difficult task. Attributes like user semantics in communication, habitat, occupation, or social network are all known to be determinant predictors of this feature. In this paper we propose three different data collection and combination methods to first estimate and, in turn, infer the socioeconomic status of French Twitter users from their online semantics. Our methods are based on open census data, crawled professional profiles, and remotely sensed, expert annotated information on living environment. Our inference models reach similar performance of earlier results with the advantage of relying on broadly available datasets and of providing a generalizable framework to estimate socioeconomic status of large numbers of Twitter users. These results may contribute to the scientific discussion on social stratification and inequalities, and may fuel several applications.

show abstract

Inferring personal economic status from social network location

Cited by 70 publications

References 28 publications

Household wealth proxies for socio-economic inequality policy studies in China

Household wealth proxies for socio-economic inequality policy studies in China

Optimal Proxy Selection for Socioeconomic Status Inference on Twitter

Location, Occupation, and Semantics Based Socioeconomic Status Inference on Twitter

Contact Info

Product

Resources

About