S
Stephanie M. Lukin
Researcher at United States Army Research Laboratory
Publications - 48
Citations - 810
Stephanie M. Lukin is an academic researcher from United States Army Research Laboratory. The author has contributed to research in topics: Narrative & Storytelling. The author has an hindex of 14, co-authored 44 publications receiving 657 citations. Previous affiliations of Stephanie M. Lukin include Loyola University Maryland & University of California.
Papers
More filters
Journal ArticleDOI
Extracting relevant knowledge for the detection of sarcasm and nastiness in the social web
TL;DR: The results show that the sarcasm detection task benefits from the inclusion of linguistic and semantic information sources, while nasty language is more easily detected using only a set of surface patterns or indicators.
Posted Content
Argument Strength is in the Eye of the Beholder: Audience Effects in Persuasion
TL;DR: The authors show that belief change is affected by personality factors, with conscientious, open and agreeable people being more convinced by emotional arguments than factual arguments, while factual arguments resonated with others.
Proceedings ArticleDOI
Argument Strength is in the Eye of the Beholder: Audience Effects in Persuasion
TL;DR: The authors show that belief change is affected by personality factors, with conscientious, open and agreeable people being more convinced by emotional arguments than factual arguments, while factual arguments resonated with others.
Book ChapterDOI
Generating Different Story Tellings from Semantic Representations of Narrative
TL;DR: The authors presented an automatic method for converting from Scheherazade's story intention graph, a semantic representation, to the input required by the personage nlg engine, using 36 Aesop Fables distributed in DramaBank.
Proceedings ArticleDOI
Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators.
TL;DR: The most explicit model can simultaneously achieve high fidelity to both semantic and stylistic goals and adds a context vector of 36 stylistic parameters as input to the hidden state of the encoder at each time step, showing the benefits of explicit stylistic supervision, even when the amount of training data is large.