People around the globe respond to major real world events through social media. To study targeted public sentiments across many languages and geographic locations, we introduce multilingual connotation frames: an extension from English connotation frames of (Rashkin et. al 2016) with 10 additional European languages, focusing on the implied sentiments among event participants engaged in a frame. As a case study, we present large scale analysis on targeted public sentiments using 1.2 million multilingual connotation frames extracted from Twitter. We rely on connotation frames to build models to forecast country-specific connotation dynamics -- perspective change over time towards salient entities and events. Our results demonstrate that connotation dynamics can be accurately predicted up to half a week in advance.

Through a particular choice of a predicate (e.g., "x violated y"), a writer can subtly connote a range of implied sentiments and presupposed facts about the entities x and y:

We introduce connotation frames as a representation formalism to organize these rich dimensions of connotation using typed relations. First, we investigate the feasibility of obtaining connotative labels through crowdsourcing experiments. We then present models for predicting the connotation frames of verb predicates based on their distributional word representations and the interplay between different types of connotative relations. Empirical results confirm that connotation frames can be induced from various data sources that reflect how language is used in context. We conclude with analytical results that show the potential use of connotation frames for analyzing subtle biases in online news media.