Features for Ranking Tweets Based on Credibility and Newsworthiness
Authors:
- Jacob RossJRJacob Ross
- Krishnaprasad ThirunarayanKTKrishnaprasad Thirunarayan
- 1 October 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. abs 1405 5, 18-25
Abstract
We create a robust and general feature set for learning to rank tweets based on credibility and newsworthiness. In previous works, it has been demonstrated that when the training and testing data are from two distinct time periods, the ranker performs poorly. We improve upon this by creating a feature set that does not overfit a particular year or set of topics. This is critical for robust analysis of social media over time. In order to derive such features, we use the studies done on credibility perception of social media as well as the clues provided in past works in this domain. We also present new features that, to our knowledge, are more effective than the state of the art.Keywords
This publication has 27 references indexed in Scilit:
- Large-Scale Linear RankSVMNeural Computation, 2014
- Cursing in English on twitter2014
- Automatic detection of rumor on Sina Weibo2012
- Evaluating Event Credibility on Twitter2012
- Modeling topic specific credibility on twitter2012
- LIBSVMACM Transactions on Intelligent Systems and Technology, 2011
- Information credibility on twitter2011
- Training linear SVMs in linear time2006
- Mining and summarizing customer reviews2004
- Cumulated gain-based evaluation of IR techniquesACM Transactions on Information Systems, 2002