Investigating the Role of Real-Time Chat Summaries in Supporting Live Streamers
Letter Of Changes: 1. Expanding on how the "Stream Assistant" supports community building within streams, as highlighted by R1: Given that the study finds that an important use of the chat is for community building, I was curious if the streamers felt that the tool supported it and if the authors had any thoughts in the discussion about this.
- **We unfortunately do not have data that directly speaks to this issue. We added following up on the impact on viewer engagement as an area of future work in the discussion.**
2. Providing more details on the prototype's design rationale, technical implementation, and operational specifics, as suggested by R1: I would have liked more information about the prototype itself: a) a stronger motivation for why they chose the features that they chose, i.e. the word clouds and emote summaries, b) how they technically implemented the various features, c) other details such as how much time it takes for the tool to generate the summaries, and how it decides what time windows to offer the streamers, etc.
- **We added additional technical details to the “Prototype Implementation” subsection.**
- **Our motivation for the polling and emotes features was based on the stream observations and prior work. We did not have any additional motivation to provide beyond this. We modified the “Word Cloud” opening to indicate that this feature was designed to provide a more comprehensive overview than the polling feature.**
3. Addressing the subjective nature of the qualitative data and exploring ways to enhance the representativeness and generalizability of the findings, as mentioned by R2.
- **We updated the last paragraph in the “Discussion” to discuss the interpretive nature of qualitative data.**
- **We also discuss generalizability to a larger sample size as an area of future work.**
4. Considering a broader range of disciplinary perspectives to provide holistic insights into the streaming experience, as recommended by R2.
- **We added a short subsection on “Social Impact of Live Streams” to the “Related Work” Section.**
Keywords: Live Streams, Chat Management, System Design, Qualitative Evaluation
TL;DR: This paper examines the role of the chatbox in live streams and investigates the effects of Stream Assistant, a tool that assists streamers with real-time chat summaries and automated polling.
Abstract: Live streaming platforms have become established communication channels where streamers and viewers can communicate through the chatbox. While there are numerous benefits to streamer-viewer interactions, managing messages can become challenging for streamers, especially during high-activity periods. In this paper, we investigate a strategy to supporting streamers that involves providing them with real-time summaries of chat messages. We investigate the feasibility of this approach through a prototype called the Stream Assistant, which provides automated poll summaries, a Word Cloud depiction of chat messages, and an overview of popular Emotes in the chat. We explore the potential utility of this approach in a multi-session study with 10 streamers, where we interviewed participants on their current chat management approaches and perceptions of the Stream Assistant after using it during one of their live streams. Our findings highlight the role of the chat in boosting engagement and audience growth and illustrate how streamers from different domains balance the chat with their activity. Our findings also indicate that many participants were enthusiastic about the Stream Assistant's lightweight polling, whereas the utility of the other features might depend on the pace of the chat and the intensity of the streamer's activities.
Submission Number: 20
Loading