Chronotome: Real-Time Topic Modeling for Streaming Embedding Spaces
This provides a tool for researchers and analysts to explore evolving themes in time-based data like social media or artistic works, though it appears incremental as it builds on existing methods.
The paper tackles the problem of capturing semantic changes over time in streaming embedding spaces by introducing Chronotome, a visualization technique that combines force-based projection and streaming clustering to create spatial-temporal maps. It demonstrates utility through use cases on text and image data, offering a new lens for understanding temporal datasets.
Many real-world datasets -- from an artist's body of work to a person's social media history -- exhibit meaningful semantic changes over time that are difficult to capture with existing dimensionality reduction methods. To address this gap, we introduce a visualization technique that combines force-based projection and streaming clustering methods to build a spatial-temporal map of embeddings. Applying this technique, we create Chronotome, a tool for interactively exploring evolving themes in time-based data -- in real time. We demonstrate the utility of our approach through use cases on text and image data, showing how it offers a new lens for understanding the aesthetics and semantics of temporal datasets.