Issue Framing in Online Discussion Fora
This work addresses the challenge of automated frame detection in online discussions, which is incremental as it adapts existing methods to a new domain.
The paper tackled the problem of detecting issue frames in online discussion fora by introducing a new annotated corpus and exploring transfer learning from newswire and social media domains, achieving results through multi-task and adversarial training with unlabeled target data.
In online discussion fora, speakers often make arguments for or against something, say birth control, by highlighting certain aspects of the topic. In social science, this is referred to as issue framing. In this paper, we introduce a new issue frame annotated corpus of online discussions. We explore to what extent models trained to detect issue frames in newswire and social media can be transferred to the domain of discussion fora, using a combination of multi-task and adversarial training, assuming only unlabeled training data in the target domain.