Differences in language use: Insights from job and talent search

Search platforms can have more than one type of user, e.g., those who provide and those who consume content. As an example, in a job/talent search platform, content providers are: (1) job seekers who provide CVs, and (2) hirers who provide job advertisements; content consumers, on the other hand, are: (3) job seekers searching for specific jobs, and (4) hirers/recruiters searching for candidates to fill particular positions. As a result, there are four types of users, each with potentially different patterns of language use. In this paper, we compare the language used by different groups of users in job/talent search, by way of word embeddings pre-trained over documents associated with distinct types of users. In doing so, we investigate whether there are systematic shifts/ mismatches in vocabulary or the use of the same term, and consider the implications for an integrated search solution. Our experiments unearth significant differences in language use, but also that there is a strong agreement between the results of our intrinsic and extrinsic comparisons of word embeddings.