Using crowdsourcing to identify a proxy of socio-economic status

Abstract

Social Media provides researchers with an unprecedented opportunity to gain insight into various facets of human life. Researchers put a great emphasis on pinpointing socioeconomic status (SES) of individuals as they can use to it to predict numerous outcomes of interest. Crowdsourcing is a term coined that entails gathering intelligence from a user community online. In order to group online users into a common conversation, researchers have made use of hashtags that will label users and user content into tags that can be easily searched for. In this paper, we propose a mechanism to group a group of users based on their geographic background and build a corpus for such users. Specifically, we have looked at online discussion forums for commercial vehicles where the website has established forums for different geographic areas to share information, have discussions, and provide additional information about the vehicle of interest. From such a discussion, it was possible to glean the vocabulary that these group of users adhere to. We compared the corpus of different communities and noted the difference in the choice of language. This provided us with the groundwork for predicting a proxy of SES of such communities. More work is underway to take words and emojis out of vocabulary (OOV) and assessing the average score as special cases.