Leveraging Semantic Facets for Adaptive Ranking of Social Comments

Abstract

An essential part of the social media ecosystem is user-generated comments. However, not all comments are useful to all people as both authors of comments and readers have different intentions and perspectives. Consequently, the development of automated approaches for the ranking of comments and the optimization of viewers' interaction experiences are becoming increasingly important. This work proposes an adaptive faceted ranking framework which enriches comments along multiple semantic facets (e.g., subjectivity, informativeness, and topics), thus enabling users to explore different facets and select combinations of facets in order to extract and rank comments that match their interests. A prototype implementation of the framework has been developed which allows us to evaluate different ranking strategies of the proposed framework. We find that adaptive faceted ranking shows significant improvements over prevalent ranking methods which are utilized by many platforms such as YouTube or The Economist. We observe substantial improvements in user experience when enriching each element of a comment along multiple explicit semantic facets rather than in a single topic or subjective facets.