Twitter power: Tweets as electronic word of mouth
Journal of the American Society for Information Science and Technology
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
The role of community and groupware in geocache creation and maintenance
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
The social honeypot project: protecting online communities from spammers
Proceedings of the 19th international conference on World wide web
Short text classification in twitter to improve information filtering
Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval
Streaming first story detection with application to Twitter
HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Twitter use by the U.S. Congress
Journal of the American Society for Information Science and Technology
Finding the storyteller: automatic spoiler tagging using linguistic cues
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
"Voluntweeters": self-organizing by digital volunteers in times of crisis
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Computing political preference among twitter followers
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
#TwitterPlay: a case study of fan roleplaying online
Proceedings of the 2013 conference on Computer supported cooperative work companion
| Hi-index | 0.01 |
The microblogging service Twitter has become an important, and sometimes primary, source of information for many users. As a forum for sharing news and discussing events, it can provide instant access to the latest updates, but this is not always welcome. In the case of television shows or live sporting events, for example, tweets about them may reveal spoilers to users in different time zones or who are delaying their viewing until later. More broadly, because Twitter is a broadcast medium, users may often want to temporarily or permanently hide content about a very specific given topic. In this paper, we describe the unique challenges to HCI, social computing, and computational linguistics posed by the task of building an interface that blocks all tweets about a specific event or topic. We illustrate some of the challenges through a pilot experiment run for three major television events: the 2009 NFC Championship football game, the 2010 mid-season finale of the show Glee, and the 2010 season premiere of the show 24. While simple techniques achieve very high recall (98%), spoilers still make it through the filter and precision is extremely poor. We conclude with a description of challenges to the community in implementing this new and increasingly important feature.