Learning Latent Local Conversation Modes for Predicting Community Endorsement in Online Discussions
This work addresses the problem of understanding community feedback in online platforms, but it is incremental as it builds on existing neural network methods with a focus on interpretability.
The paper tackles predicting community endorsement in online discussions by integrating participant response structure and comment text, achieving improved prediction accuracy with interpretable latent modes.
Many social media platforms offer a mechanism for readers to react to comments, both positively and negatively, which in aggregate can be thought of as community endorsement. This paper addresses the problem of predicting community endorsement in online discussions, leveraging both the participant response structure and the text of the comment. The different types of features are integrated in a neural network that uses a novel architecture to learn latent modes of discussion structure that perform as well as deep neural networks but are more interpretable. In addition, the latent modes can be used to weight text features thereby improving prediction accuracy.