A groundbreaking study conducted by researchers at Queen Mary University of London has revealed that people’s income can be accurately predicted solely based on their social media posts. The study, which analyzed a massive dataset of 2.6 million posts from the popular social networking site Nextdoor, uncovered significant differences in the content shared by individuals residing in affluent neighborhoods compared to those in less privileged areas. This finding suggests that our online activities, beyond just Nextdoor, offer valuable insights into our socioeconomic status, potentially enabling user profiling.
The implications of this knowledge are far-reaching. Social media platforms could utilize users’ income information to recommend content that aligns with their socioeconomic standing. Advertisers and e-commerce businesses, in particular, could leverage this economic profiling to effectively target consumers by promoting products tailored to their income levels.
Interestingly, the study also found that residents of wealthier neighborhoods tend to share positive posts but engage in more discussions about crime, even in areas with lower actual crime rates than less affluent neighborhoods. Dr. Ignacio Castro, the lead researcher and Lecturer in Data Analytics at Queen Mary University of London, highlighted this disparity, stating, “Our study demonstrates that text generated by users in poorer neighborhoods can be distinguished from that produced in wealthier neighborhoods. While crime-sensitive posts are more prevalent in wealthier areas, overall, posts from these neighborhoods exhibit a more positive sentiment.”
Published on 2 June in the Proceedings of the International AAAI Conference on Web and Social Media, this study marks the first large-scale exploration of Nextdoor, shedding light on how income levels and inequality within neighborhoods manifest in the online realm. The researchers collected and analyzed 2.6 million posts from 64,283 neighborhoods in the United States and 3,325 neighborhoods in the United Kingdom, shared on Nextdoor between November 2020 and September 2021. The findings remained consistent across both countries.
The study also revealed that residents of wealthier neighborhoods show heightened concern about crime, with the top 20% of affluent neighborhoods discussing crime approximately 1.5 times more than the poorest neighborhoods. Interestingly, this trend persists despite the fact that crime rates are 1.3 times higher in less privileged neighborhoods. Furthermore, discussions surrounding non-violent crimes surpass those about violent crimes. While most user content trends were similar between the US and the UK, the study identified a notable distinction regarding discussions on weapons and violent crimes, which were more prevalent in the US’s wealthier neighborhoods compared to the UK. This discrepancy did not extend to middle-income neighborhoods, as UK residents displayed a higher tendency to post about this type of crime than their US counterparts.
Citation: “Lady and the Tramp Nextdoor: Online Manifestations of Real-World Inequalities in the Nextdoor Social Network” by Waleed Iqbal, Vahid Ghafouri, Gareth Tyson, Guillermo Suarez-Tangil, and Ignacio Castro, 2 June 2023, Proceedings of the Seventeenth International AAAI Conference on Web and Social Media.
Table of Contents
Frequently Asked Questions (FAQs) about Socioeconomic standing
How was income prediction done based on social media posts?
The income prediction in the study was conducted by analyzing the content of social media posts, specifically on the Nextdoor platform. Researchers at Queen Mary University of London examined 2.6 million posts and identified prominent disparities in the type of content posted by residents of affluent and less affluent neighborhoods. This analysis allowed them to accurately predict a user’s income based on the patterns and characteristics of their posts.
What are the potential implications of predicting income from social media posts?
The accurate prediction of income from social media posts opens up various possibilities. Social media platforms could suggest content that aligns with a user’s income level, enhancing their user experience. Advertisers and e-commerce businesses could also benefit by utilizing economic profiling to target consumers more effectively, promoting specific products at varying prices corresponding to the user’s income level.
What were the notable findings of the study?
The study revealed that wealthier neighborhoods displayed more positive posts but engaged in more discussions about crime, even with lower actual crime rates compared to poorer neighborhoods. The research also highlighted regional differences in crime discussions, with wealthy areas in both the US and the UK talking about crime more, particularly focusing on weapons and violent crimes in the US. Non-violent crimes were discussed more frequently overall. These findings shed light on the manifestation of income levels and inequality within neighborhoods in online spaces.
How was the study conducted, and what was the sample size?
The study collected and analyzed 2.6 million posts from 64,283 neighborhoods in the United States and 3,325 neighborhoods in the United Kingdom shared on the Nextdoor platform. The data spanned from November 2020 to September 2021. With a large sample size, this study provided insights into income prediction and socioeconomic factors across different regions and countries.
What is the reference for this study?
The study titled “Lady and the Tramp Nextdoor: Online Manifestations of Real-World Inequalities in the Nextdoor Social Network” was conducted by Waleed Iqbal, Vahid Ghafouri, Gareth Tyson, Guillermo Suarez-Tangil, and Ignacio Castro. It was published on 2 June 2023 in the Proceedings of the Seventeenth International AAAI Conference on Web and Social Media.
More about Socioeconomic standing
- Queen Mary University of London: Website
- Nextdoor: Official Website
- Proceedings of the International AAAI Conference on Web and Social Media: Conference Website
- “Lady and the Tramp Nextdoor: Online Manifestations of Real-World Inequalities in the Nextdoor Social Network” – Research Paper: [Link](to be provided)
5 comments
omg income prediction from social media is cray! so now they can target ads to ppl based on how much money they make? that’s like next level advertising. i’m curious to see if this becomes a thing on other platforms too.
this study shows the power of social media in understanding people’s lives. who would’ve thought you could predict income just from posts? now i’m wondering if my social media can tell someone how much money i make. better watch what i share!
i’d love to read the full research paper! it must have so much more detailed info. the fact that they looked at 2 countries and found similar trends is interesting. can’t wait to see how this kind of analysis develops in the future.
fascinating research! it’s amazing how our online activities can reveal so much about our socioeconomic status. and the fact that wealthier neighborhoods talk more about crime, even if they have lower actual crime rates, is mind-blowing. gotta be careful what we post online!
wow this study is super cool! they analized 2.6 million posts on Nextdoor and found out you can predict income just by reading ppl’s posts. that’s wild! i wonder what other stuff they can find out from social media.