JUNGLE is an interactive, visual platform for the collaborative manipulation and consumption of nonlinear transmedia stories. Intuitive visual interfaces encourage JUNGLE users to explore vast libraries of story worlds, expand existing stories, or conceive of entirely original story worlds. JUNGLE stories utilize multiple media forms including videos, images, and text, and accommodate branching narrative outcomes. We extensively evaluate Jungle using a focused small-scale study and free-form large-scale study with careful protection of study participant privacy. In the small-scale study, users found JUNGLE ’s features to be versatile, engaging, and intuitive for discovering new content. In the large-scale study, 354 subjects tested JUNGLE in a realistic 45-day scenario. We find that users collaborated on story worlds incorporating various forms of media in multiple (on average two) possible story paths. In particular, we find through initial observations that JUNGLE can evoke creativity: traditionally passive consumers gradually transition into active content creators. Supplementary videos showcasing the JUNGLE system and hypothetical example stories authored using JUNGLE independently hosted here and here.

Storyprint is an interactive visualization of creative storytelling that facilitates individual and comparitive structural analyses. This visualization method is intended for script-based media, which has suitable metadata. The visualization is presented as a radial diagram of concentric rings wrapped around a circular time axis. A user then has the ability to toggle a difference overlay to assist in the cross-comparison of two different scene inputs.

We propose an end-to-end network for visual illustration of a sequence of sentences forming a story. At the core of our model is the ability to model the inter-related nature of the sentences within a story, as well as the ability to learn coherence to support reference resolution. The framework takes the form of an encoder-decoder architecture, where sentences are encoded using a hierarchical two-level sentence-story GRU, combined with an encoding of coherence, and sequentially decoded using a predicted feature representation into a consistent illustrative image sequence. We optimize all parameters of our network in an end-to-end fashion with respect to order embedding loss, encoding entailment between images and sentences. Experiments on the VIST storytelling datasetV highlight the importance of our algorithmic choices and efficacy of our overall model.