Interactive Concept Learning for Uncovering Latent Themes in Large Text Collections
This addresses the problem for experts in diverse disciplines who need to analyze large text collections, offering an incremental improvement over traditional unsupervised or manual methods.
The paper tackles the challenge of uncovering latent themes in large text collections by expanding the definition of a theme to include expert-relevant concepts and proposing an interactive framework that balances automation with manual control, reducing manual effort.
Experts across diverse disciplines are often interested in making sense of large text collections. Traditionally, this challenge is approached either by noisy unsupervised techniques such as topic models, or by following a manual theme discovery process. In this paper, we expand the definition of a theme to account for more than just a word distribution, and include generalized concepts deemed relevant by domain experts. Then, we propose an interactive framework that receives and encodes expert feedback at different levels of abstraction. Our framework strikes a balance between automation and manual coding, allowing experts to maintain control of their study while reducing the manual effort required.