Abstract
As the number of personal broadcasting contents is rapidly increasing, the demand for a service that provides highlights is growing. A highlight, a collection of interesting scenes, can improve the quality of viewing experience. In this paper, we propose a method to automatically detect highlights using only chat traffic information. We also propose evaluation methods the effectiveness of using chat traffic in highlight detection. We apply the detection algorithm to game broadcasting, which has larger audience, and demonstrate its performance.
| Translated title of the contribution | Highlight Detection in Personal Broadcasting by Analysing Chat Traffic : Game Contests as a Test Case |
|---|---|
| Original language | Korean |
| Pages (from-to) | 218-226 |
| Number of pages | 9 |
| Journal | 방송공학회 논문지 |
| Volume | 23 |
| Issue number | 2 |
| DOIs | |
| State | Published - 2018 |