| Popis: |
The traditional methods of evaluation of data cannot be used to evaluate the quality of the streaming twitter data due to the restriction on access to historic tweets, and dynamic nature of the microblogging posts. For this purpose, we propose a novel method to quantify the quality of data independent of the underlying model. Using the change in velocity of tweets with addition of search terms, and the relevance computed by the underlying model, we evaluated the impact of each search term on the quality of data retrieved. |
