Submissions/Hey, it's Trending! Let's Update that Wikipedia Article!
This is an accepted submission for Wikimania 2012. |
- Submission no.
144
- Title of the submission
Hey, it's Trending! Let's Update that Wikipedia Article!
- Type of submission (workshop, tutorial, panel, presentation)
Presentation
- Author of the submission
Arkaitz Zubiaga, Taylor Cassidy, Heng Ji
- E-mail address
arkaitz at zubiaga dot org
- Username
- Country of origin
United States
- Affiliation, if any (organization, company etc.)
City University of New York
- Personal homepage or blog
- Abstract (at least 300 words to describe your proposal)
Much of the information contained on Wikipedia must be updated regularly according to news given by current affairs. To assist the need to update contents in an efficient way, we are exploring how the collection of real-time data from Twitter can help. Tweets posted by users can provide, in some cases, relevant information that suggest to update some Wikipedia article(s). It has been shown that Twitter many times breaks news even earlier than news media.
As a first approach to develop a system that suggests updates on Wikipedia according to tweets, we are working on Twitter's trending topics. A trending topic is a conversation that experiences a sudden increase in the amount of tweets, and thus means that, for some reason, it becomes a popular topic being mentioned outstandingly. We rely on the fact that trending topics might be suggesting that some news occurred, and that related Wikipedia contents should be updated. We aim to discover those topics in the early stage as they emerge, allowing to suggest what Wikipedia pages to update. To tackle the task, we follow a 2-step process:
- The first step determines whether a newly-emerging trending topic is newsworthy. We make use of some social and linguistic patterns to do so. If the system considers it is newsworthy, we go through the second step. Otherwise, the system discards the trending topic as irrelevant.
- The second step performs the so-called "wikification of a trending topic". Given a newsworthy trending topic as an input, the system looks for the top Wikipedia pages that should be updated with new information. As an output, the system provides the top Wikipedia pages to be updated, as well as a link to be included as a citation, when available.
This process would help update Wikipedia contents very quickly as news break, letting editors know about changes to be done.
At Wikimania 2012, we would like to present the goals, details of the system, and progress of this research project we are carrying out at the City University of New York.
- Track
Research, Analysis, and Education
- Length of presentation/talk
25 Minutes
- Will you attend Wikimania if your submission is not accepted?
Yes
- Slides or further information (optional)
- Special request as to time of presentations
Interested attendees
If you are interested in attending this session, please sign with your username below. This will help reviewers to decide which sessions are of high interest. Sign with four tildes. (~~~~).