Research Bites: "Inferring User Demographics and Social Strategies in Mobile Social Networks"
As part of our "Research Bites" series, in which we ask data science researchers to spend five minutes telling us in their own words about their work, and opportunities for practical applicability in the context of sustainable development or humanitarian action, today we hear from researchers Nitesh V. Chawla, Yuxiao Dong, Yang Yang and Jie Tang from the Department of Computer Science and Engineering and the Interdisciplinary Center for Network Science and Applications at the University of Notre Dame and the Department of Computer Science and Technology at Tsinghua University.
Inferring User Demographics and Social Strategies in Mobile Social Networks
Demographics are widely used in marketing to characterize different types of customers. However, in practice, demographic information such as age, gender, and location of a mobile phone user is usually unavailable due to privacy and other reasons. This research seeks to automatically infer users’ demographics based on their daily mobile communication patterns. The study is based on analysis of a real-world large mobile network of more than 7,000,000 users and over 1,000,000,000 communication records. The study shows that older people have a steady social circle, while young people expand theirs. Women make more cross-generational interactions such as phoning or texting older family members. The 'WhoAmI' method developed in this research seeks to predict gender and approximate age of the user.
The full research paper can be accessed online here.
1. Tell us about your research paper in two sentences
We unveil the demographic-based social strategies in human communication and develop the WhoAmI method to infer users’ demographic profiles automatically based on their social connections.
2. Why do your findings matter?
Our findings - the significant social strategies in human communication - offer a great potential for understanding human social behaviors with respect to different groups of individuals. For example, we find that (1) young people are active in broadening their social circles, while seniors tend to keep small but close connections; (2) people’s attention to opposite-gender connections quickly disappears after entering into 35 years old, while the insistence and social investment on same-gender social groups lasts for a lifetime. The discoveries characterize the properties of human communications regarding to the demographic profiles and further show us how the social strategies change over time by which social needs are satisfied.
3. How could this research be put into practice?
As a direct application in telecommunications, our methodology can be applied into the prediction of demographic profiles for prepaid users of mobile operators, since the prepaid users have high potential to switch to a different operator. 95% of mobile users in India are prepaid, 80% in Latin America, 70% in China, 65% in Europe, and 33% in the U.S. Even in the U.S., the switch to prepaid plans is accelerating during the economic recession from 2008. Knowledge of the connections of individuals with different demographic profiles will allow us to model the flow and migration of the work force vis-à-vis the socio-economic conditions in different regions/countries of the world.
4. Why did you select this topic to research?
Big data is providing an unprecedented opportunity to understand the principles underpin the highly connected world, from individuals to societies. We are passionate about Big Data for the common good, and how data can be leveraged to derive insights about societies and human welfare.
The researchers will be on hand to answer questions in the comments section below, so we invite practitioners from the development or humanitarian sectors to join the discussion!