Papers with 2012
Optimising Twitter-based Political Election Prediction with Relevance andSentiment Filters (2020.lrec-1)
Copied to clipboard
| Challenge: | A set of over 17,000 tweets containing political party names were annotated by at least three annotators per tweet on ten features denoting communicative intent. |
| Approach: | They propose to annotate tweets containing political party names by using oracle filters to achieve lower MAEs. |
| Outcome: | The proposed method achieves a mean absolute error (MAE) of 2.71% for 2012 and 2.02% for 2012, and 2.89% for 2015 for the Dutch elections. |