Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ReelFramer: Human-AI Co-Creation for News-to-Video Translation

Sitong Wang, Samia Menon, Tao Long, Keren Henderson, Dingzeyu Li, Kevin Crowston, Mark Hansen, Jeffrey V. Nickerson, Lydia B. Chilton

TL;DR

ReelFramer, a human-AI co-creative system that helps journalists translate print articles into scripts and storyboards, is introduced and the benefits of using narrative framing and foundational details in content retargeting are discussed.

Abstract

Short videos on social media are the dominant way young people consume content. News outlets aim to reach audiences through news reels -- short videos conveying news -- but struggle to translate traditional journalistic formats into short, entertaining videos. To translate news into social media reels, we support journalists in reframing the narrative. In literature, narrative framing is a high-level structure that shapes the overall presentation of a story. We identified three narrative framings for reels that adapt social media norms but preserve news value, each with a different balance of information and entertainment. We introduce ReelFramer, a human-AI co-creative system that helps journalists translate print articles into scripts and storyboards. ReelFramer supports exploring multiple narrative framings to find one appropriate to the story. AI suggests foundational narrative details, including characters, plot, setting, and key information. ReelFramer also supports visual framing; AI suggests character and visual detail designs before generating a full storyboard. Our studies show that narrative framing introduces the necessary diversity to translate various articles into reels, and establishing foundational details helps generate scripts that are more relevant and coherent. We also discuss the benefits of using narrative framing and foundational details in content retargeting.

ReelFramer: Human-AI Co-Creation for News-to-Video Translation

TL;DR

ReelFramer, a human-AI co-creative system that helps journalists translate print articles into scripts and storyboards, is introduced and the benefits of using narrative framing and foundational details in content retargeting are discussed.

Abstract

Short videos on social media are the dominant way young people consume content. News outlets aim to reach audiences through news reels -- short videos conveying news -- but struggle to translate traditional journalistic formats into short, entertaining videos. To translate news into social media reels, we support journalists in reframing the narrative. In literature, narrative framing is a high-level structure that shapes the overall presentation of a story. We identified three narrative framings for reels that adapt social media norms but preserve news value, each with a different balance of information and entertainment. We introduce ReelFramer, a human-AI co-creative system that helps journalists translate print articles into scripts and storyboards. ReelFramer supports exploring multiple narrative framings to find one appropriate to the story. AI suggests foundational narrative details, including characters, plot, setting, and key information. ReelFramer also supports visual framing; AI suggests character and visual detail designs before generating a full storyboard. Our studies show that narrative framing introduces the necessary diversity to translate various articles into reels, and establishing foundational details helps generate scripts that are more relevant and coherent. We also discuss the benefits of using narrative framing and foundational details in content retargeting.
Paper Structure (56 sections, 8 figures, 3 tables)

This paper contains 56 sections, 8 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. News Reels and Narrative Framing
  4. Automated Narrative Generation
  5. Computational Storyboarding
  6. Human-AI Co-creativity
  7. Co-Design with Journalists
  8. Types of News Reels to Support
  9. Target User Group
  10. Creation Process to Support
  11. Developing Narrative Framings
  12. Developing Scripts
  13. Developing Storyboards
  14. Expert Evaluation of LLM Capabilities
  15. Data Preparation
  16. ...and 41 more sections

Figures (8)

  • Figure 1: Screenshot of ReelFramer Stage 1: Scriptwriting: 1) extract news information, 2) generate and edit script premises, and 3) generate and edit scripts. Users can regenerate suggestions in the first step, and in the subsequent two steps, they can choose to accept, regenerate, or edit the suggestions.
  • Figure 2: Screenshot of ReelFramer Stage 2: Storyboarding---character board
  • Figure 3: Screenshot of ReelFramer Stage 2: Storyboarding---storyboard
  • Figure 4: An expository dialog news reel created in our user study for an article about The Willow Project.
  • Figure 5: A reenactment news reel created in our user study for an article about The Willow Project.
  • ...and 3 more figures