RoTuEl: a semi-automated method for labeling political tweets
Wilton De Paula Filho, Ana Cristina Bicharra García · International Conference on Artificial Intelligence · 2015
The latest research on prediction of the outcome of elections using Twitter data, the election tweets labeling area has hardly been explored. Therefore, the authors of this paper propose to develop a semi-automatic model for labeling political tweets. The expected result of this study is to contribute to enhance the quality of the choice of message used in the labeling process by reducing the time selection of messages and the efficiency of classifying the messages and, thus, to increase the accuracy of the models using this approach. The proposed method could lable 2200 messages from the analysis of only 60 messages by 20 users. The first results obtained by the method were higher than the process carried out manually by humans.