Cultural values data from textual online sources using word embedding models: Some online values are highly correlated with the corresponding offline values, especially religion-related ones

Measuring International Online Human Values with Word Embeddings. Gabriel Magno, Virgilio Almeida. ACM Transactions on the Web, Vol. 16, No. 2. May 2022 Article No.: 9pp 1–38, online Dec 22 2021. https://doi.org/10.1145/3501306

Abstract: As the Internet grows in number of users and in the diversity of services, it becomes more influential on peoples lives. It has the potential of constructing or modifying the opinion, the mental perception, and the values of individuals. What is being created and published online is a reflection of people’s values and beliefs. As a global platform, the Internet is a great source of information for researching the online culture of many different countries. In this work we develop a methodology for measuring data from textual online sources using word embedding models, to create a country-based online human values index that captures cultural traits and values worldwide. Our methodology is applied with a dataset of 1.7 billion tweets, and then we identify their location among 59 countries. We create a list of 22 Online Values Inquiries (OVI), each one capturing different questions from the World Values Survey, related to several values such as religion, science, and abortion. We observe that our methodology is indeed capable of capturing human values online for different counties and different topics. We also show that some online values are highly correlated (up to c = 0.69, p < 0.05) with the corresponding offline values, especially religion-related ones. Our method is generic, and we believe it is useful for social sciences specialists, such as demographers and sociologists, that can use their domain knowledge and expertise to create their own Online Values Inquiries, allowing them to analyze human values in the online environment.