Constructing effective and efficient topic-specific authority networks for expert finding in social media

Reyyan Yeniterzi, Jamie Callan

Abstract: Authority-based approaches are widely used in expert retrieval from social media. However, most of these approaches are applied to either topic-independent networks, or more topic-dependent networks which still contain topic-irrelevant users as nodes and interactions as edges. Therefore, authority estimation over these graphs is still not topic-specific enough. This paper proposes a more topic-focused authority network construction approach which provides more effective topic-specific authority modeling of users. Focusing the computational effort to more topic-specific authority networks also leads to significant gains in running time for authority estimation.