Tracking and Understanding Cultural Values using Big Data

Word usage patterns can often be identified over groups of people, and while these patterns are sometimes correlated with emotional states or personality, there are also many linguistic patterns that reflect the values of a given culture. The goal of this project is to gather new insights into the underlying values of select cultures, by combining the understanding of human perception as obtained through psychological analyses with the large-scale linguistic processing enabled by current state-of-the-art tools in computational linguistics. The project has two specific objectives. First, it will build computational linguistic models that can automatically discover differences in cultural values, by identifying patterns in concept usage for different cultures, and applying these models on a large scale. Second, it will validate the findings of these computational models through psychological qualitative and quantitative methods in laboratory and field studies. The project is expected to have far reaching implications, as it will enable a new understanding of ourselves as diverse cultures of the world. It will also make possible several applications, such as efficient communication between people belonging to different cultures, and identification and understanding of cross-cultural behaviors, intentions, and believes. Moreover, the resources that will be generated in this project (datasets and software tools) will be made publicly available on a dedicated website, thus enabling future research as well as educational projects concerned with analyzing and understanding cultural values and diversity.