Papers by Sarah Shugars

2 papers
(Mis)alignment Between Stance Expressed in Social Media Data and Public Opinion Surveys (2021.emnlp-main)

Copied to clipboard

Challenge: Existing stance detection methods have been evaluated in comparison to the public opinion data they promise to replace.
Approach: They propose to compare an individual's self-reported stance to the stance inferred from their social media data.
Outcome: The proposed models are compared to a public opinion survey with 1,129 individuals across four salient targets.
Microblog Conversation Recommendation via Joint Modeling of Topics and Discourse (N18-1)

Copied to clipboard

Challenge: Existing methods for recommendation focus on content of individual posts, but we exploit both context and user content and behavior preferences.
Approach: They propose a method that captures conversational context and user content and behavior preferences.
Outcome: The proposed method outperforms methods that only model content without considering discourse on two Twitter datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations