How Hierarchical Topics Evolve in Large Text Corpora

Abstract

Using a sequence of topic trees to organize documents is a popular way to represent hierarchical and evolving topics in text corpora. However, following evolving topics in the context of topic trees remains difficult for users. To address this issue, we present an interactive visual text analysis approach to allow users to progressively explore and analyze the complex evolutionary patterns of hierarchical topics. The key idea behind our approach is to exploit a tree cut to approximate each tree and allow users to interactively modify the tree cuts based on their interests. In particular, we propose an incremental evolutionary tree cut algorithm with the goal of balancing 1) the fitness of each tree cut and the smoothness between adjacent tree cuts; 2) the historical and new information related to user interests. A time-based visualization is designed to illustrate the evolving topics over time. To preserve the mental map, we develop a stable layout algorithm. As a result, our approach can quickly guide users to progressively gain profound insights into evolving hierarchical topics. We evaluate the effectiveness of the proposed method on Amazon's Mechanical Turk and real-world news data. The results show that users are able to successfully analyze evolving topics in text data.

Modern trends in visualization of collections of scientific publications

“…В случае больших коллекций документов с большим количеством тем, их принято организовывать иерархически с применением модели Байесовское розо-дерево BRT [9], которая использует байесовский алгоритм иерархической кластеризации для построения дерева тем с произвольным коэффициентом ветвления, в котором каждая нелистовая вершина изображает кластер тем. Примерами систем визуализации, использующих иерархическое представление моделей тем являются TopicPanorama и HierarchicalTopics [10][11]. Однако общим недостатком всех вариаций модели LDA является высокие требования к производительности.…”

VisOHC: Designing Visual Analytics for Online Health Communities

“…In addition to topic extraction, some researchers have attempted to encode temporal information. Cui et al [11] employed a trend chart to encode the changes in document sentiment over time. Xu et al [40] emphasized competition between different topics with inter-crossing multiple trend lines.…”

A Survey On Interactivity in Topic Models

“…As mentioned, LDA requires several input parameters, the smoothing variables β, α and the number of topics K. There are no strict guidelines for setting these parameters; tuning Graph based Topicnets [16], ParallelTopics [17], LDAVis [18], LDAexplore [19], TopicPanorama [20], S. Rönnqvist, et al [4], Hierarchie [21] Time Visualisation TextFlow [22], TIARA [23], ThemeRiver [24], RoseRiver [25] (IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 7, No.…”

“…It is also highly interactive, allowing users to discover what causes the birth, death, splitting and merging of topics throughout the time period of the associated corpus. Roseriver [25] further builds upon the work in [22], using a similar river-flow visual representation, but employs a hierarchical topic model in order to better describe large corpus, and for providing users with different overview levels as desired.…”