Making Sense of Group Chat through Collaborative Tagging and Summarization
Citations Over TimeTop 1% of 2018 papers
Abstract
While group chat is becoming increasingly popular for team collaboration, these systems generate long streams of unstructured back-and-forth discussion that are difficult to comprehend. In this work, we investigate ways to enrich the representation of chat conversations, using techniques such as tagging and summarization, to enable users to better make sense of chat. Through needfinding interviews with 15 active group chat users, who were shown mock-up alternative chat designs, we found the importance of structured representations, including signals such as discourse acts. We then developed Tilda, a prototype system that enables people to collaboratively enrich their chat conversation while conversing. From lab evaluations, we examined the ease of marking up chat using Tilda as well as the effectiveness of Tilda-enabled summaries for getting an overview. From a field deployment, we found that teams actively engaged with Tilda both for marking up their chat as well as catching up on chat.
Related Papers
- → Mining Sequential Update Summarization with Hierarchical Text Analysis(2016)6 cited
- → An auto-encoder-based summarization algorithm for unstructured videos(2017)3 cited
- Research of Automatic Summarization Methods(2011)
- Video Summarization Based on the "Entities-Description-Utilities" Model(2005)
- Susquehanna Chorale Spring Concert "Roots and Wings"(2017)