Work

TATA: Stance Detection via Topic-Agnostic and Topic-Aware Embeddings

Year: 2023

Type: conference-paper

Abstract: Stance detection is important for understanding different attitudes and beliefs on the Internet.However, given that a passage's stance toward a given topic is often highly dependent on that topic, building a stance detection model that generalizes to unseen topics is difficult.In this work, we propose using contrastive learning as well as an unlabeled dataset of news articles that cover a variety of different topics to train topic-agnostic/TAG and topic-aware/TAW embeddings for use in downstream stance detection.Combining these embeddings in our full TATA model, we achieve state-of-the-art performance across several public stance detection datasets (0.771 F 1 -score on the Zero-shot VAST dataset).We release our code and data at https://github.com/hanshanley/tata.

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.18653/v1/2023.emnlp-main.694

Authors: Hans Hanley, Zakir Durumeric

Institution: Stanford University

Language: English

Topic: Sentiment Analysis and Opinion Mining

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Science Foundation

Awards: G2911450482, Graduate Research Fellowship Program (GRFP)