Ranking Content based on Semantic Dimensions
Jason Cohn, Siddharth Muthukumaran, Larry J. Birnbaum · 2017
Whether it's a social media system populating a news feed or a user searching for content to share, decisions are constantly being made on the basis of semantic information. Topic, sentiment, and preference are among the many semantic dimensions of content that humans and machines must carefully weigh when prioritizing media consumption. Though easy for humans, such natural language tasks are nontrivial computationally. In this paper, we present a novel technique for sorting a corpus of news articles based on two competing semantic objectives. Solving this multi-objective optimization problem yields a pareto front with a finite set of solution articles. Iterating on the remaining data, we construct solution sets in tiers of successive pareto fronts. Our technique allows for exploration of the tradeoffs between semantic concepts, yielding cogent and trope-like results.