Connotation Frames: A Data-Driven Investigation

By Hannah Rashkin, Sameer Singh, Yejin Choi. 2015

95 citations recorded by the source corpus.

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: (1) writer's perspective: projecting x as an "antagonist"and y as a "victim", (2) entities' perspective: y probably dislikes x, (3) effect: something bad happened to y, (4) value: y is something valuable, and (5) mental state: y is distressed by the event. 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 people use language and give rise to the connotative meanings. We conclude with analytical results that show the potential use of connotation frames for analyzing subtle biases in online news media.

Subfields: Natural Language Processing, Sentiment & Opinion Analysis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Sentiment & Opinion Analysis

Citations in the corpus

Probing for semantic evidence of composition by means of simple classification tasks (2016, methodology): “Possible approaches to estimating plausibility without human annotation include using n-gram statistics on simple argument/predicate combinations (Rashkin et al., 2016) or making use of se-lectional preference modeling (Resnik, 1996; Erk, 2007; S´eaghdha, 2010).”
Finding Microaggressions in the Wild: A Case for Locating Elusive Phenomena in Social Media Posts (2019, background): “This moderate agreement is on-par with other difﬁcult annotation tasks, such as those for connotation frames (Rashkin et al., 2016), which had 0.52 percentage agreement for rating the polarity of the sentence towards a target, dimensions of social relationships (Rashid and Blanco, 2017), which had…”
Connotation Frames of Power and Agency in Modern Films (2017, background): “Note that a similar difference between KA scores and soft percent agreement was found in our previous connotation frame work (Rashkin et al., 2016).”
PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction (2020, background): “Connotation frames (Rashkin et al., 2016; Sap et al., 2017) distill implicit relations between a verb, its agent, and its theme.”
Addressing the Winograd Schema Challenge as a Sequence Ranking Task (2018, methodology): “As additional matrix-type features we experiment with dependency edge sequences and information about the connotation of the arguments induced by their predicate as stated in the resource Connotation Frames (Rashkin et al., 2015; Rashkin et al., 2016).”
A Framework for the Computational Linguistic Analysis of Dehumanization (2020, methodology): “Scores are calculated for each subject-verb-object triple containing these group labels as the writer’s perspective towards the subject or object (depending on the group label’s position) based on the head verb’s entry in the Connotation Frames lexicon (Rashkin et al., 2016).”
Event2Mind: Commonsense Inference on Events, Intents, and Reactions (2018, background): “…Schuler et al., 2009; Hartshorne et al., 2013, inter alia ), implicitly connoted by events (Reisinger et al., 2015; White et al., 2016; Greene, 2007; Rashkin et al., 2016), or sentiment polarities of events (Ding and Riloff, 2016; Choi and Wiebe, 2014; Russo et al., 2015; Ding and Riloff, 2018).”
Entity-Centric Contextual Affective Analysis (2019, methodology): “Furthermore, unlike the connotation frame annotations (Rashkin et al., 2016; Sap et al., 2017), the VAD lexicons used in this work were speciﬁcally motivated by social psychology literature on this topic, which inﬂuenced the annotation scheme (Mohammad, 2018).”
The Importance of Modeling Social Factors of Language: Theory and Practice (2021, background): “Rashkin et al. (2016) showed the value of modelling speaker perspective to discover opinions or biases in the way things are expressed.”