Interactive Topic Modeling

By Yuening Hu, Jordan L. Boyd-Graber, Brianna Satinoff. Annual Meeting of the Association for Computational Linguistics, 2011

296 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/b91eaf4dd0283f6b444a88023b04deb2b955f89d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Soujanya Poria
2. Bing Liu
3. Erik Cambria
4. Shuai Wang
5. B. Liu
6. Zhiyuan Chen
7. Zixuan Ke
8. Hu Xu

Citations in the corpus

• Aspect extraction for opinion mining with a deep convolutional neural network (2016, methodology): “Topic modeling has been widely used as a basis to perform extraction and grouping of aspects (Hu et al., 2014; Chen and Liu, 2014).”
• Mining Aspect-Specific Opinion using a Holistic Lifelong Topic Model (2016, methodology): “Since our LAST model can exploit prior aspect and opinion knowledge, it is thus related to knowledge-based topic models such as [2, 18, 41, 33, 17].”
• Aspect Extraction through Semi-Supervised Modeling (2012, methodology): “Hu et al. (2011) relied on user feedback during Gibbs sampling iterations.”
• A Survey of Human-in-the-loop for Machine Learning (2021, background): “[91] extend a statistical framework [100] to allow end-users to add, remove, or change the weights of words within each topic.”
• UTOPIAN: User-Driven Topic Modeling Based on Interactive Nonnegative Matrix Factorization (2013, background): “As noted in recent work in the machine learning domain [1, 20], incorporating domain knowledge into topic modeling via user interactions can be a cumbersome process.”
• Mining topics in documents: standing on the shoulders of big data (2014, background): “, [1, 2, 9, 10, 14, 15, 26, 28]) can exploit such prior domain knowledge to produce better topics.”
• Interpretable Machine Learning : Lessons from Topic Modeling (2016, background): “There has even been research on incorporating such preferences interactively, allowing users to change topics during the inference procedure [11].”
• Applications of Topic Models (2017, background): “Hu et al. [2014b] bring existing tree-based Latent Dirichlet Allocation (tlda) and polylingual Latent Dirichlet Allocation (plda) together and create the polylingual tree-based Latent Dirichlet allocation (ptlda) that incorporates both word-level correlations and document-level alignment information”
• Interactive Machine Learning via a GPU-accelerated Toolkit (2017, background): “Systems like [37, 18] also allow users to iteratively refine the model based on their preference.”
• Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda (2018, methodology): “visualization techniques for text analysis [34, 35], tools to support interactive data analysis [24, 25, 37] and interactive machine learning [82].”