Junjie H. Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Junjie H. Xu has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Kojiro Iizuka
Gunosy Inc Japan
1 shared publication - Lingrong Kong
The University of Tokyo, Tokyo, Japan
1 shared publication - Yu Nakano
University of Tsukuba, Japan
1 shared publication
Latest Publications
- Open Access
- 19 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 422-426
CS-lol: a Dataset of Viewer Comment with Scene in E-sports Live-streaming
Billions of live-streaming viewers share their opinions on scenes they are watching in real-time and interact with the event, commentators as well as other viewers via text comments. Thus, there is necessary to explore viewers’ comments with scenes in E-sport live-streaming events. In this paper, we developed CS-lol, a new large-scale dataset containing comments from viewers paired with descriptions of game scenes in E-sports live-streaming. Moreover, we propose a task, namely viewer comment retrieval, to retrieve the viewer comments for the scene of the live-streaming event. Results on a series of baseline retrieval methods derived from typical IR evaluation methods show our task as a challenging task. Finally, we release CS-lol and baseline implementation to the research community as a resource.
- 19 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 422-426
Open AccessCS-lol: a Dataset of Viewer Comment with Scene in E-sports Live-streaming
Billions of live-streaming viewers share their opinions on scenes they are watching in real-time and interact with the event, commentators as well as other viewers via text comments. Thus, there is necessary to explore viewers’ comments with scenes in E-sport live-streaming events. In this paper, we developed CS-lol, a new large-scale dataset containing comments from viewers paired with descriptions of game scenes in E-sports live-streaming. Moreover, we propose a task, namely viewer comment retrieval, to retrieve the viewer comments for the scene of the live-streaming event. Results on a series of baseline retrieval methods derived from typical IR evaluation methods show our task as a challenging task. Finally, we release CS-lol and baseline implementation to the research community as a resource.