Publication

Determining the Function of Political Tweets

Sang, E. T. K., Kruitbosch, H., Broersma, M. & Del Valle, M. E., 14-Nov-2017, Proceedings - 13th IEEE International Conference on eScience, eScience 2017. Institute of Electrical and Electronics Engineers Inc., p. 438-439 2 p. 8109165

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Copy link to clipboard

Documents

  • Determining the Function of Political Tweets

    Final publisher's version, 107 KB, PDF document

DOI

We study the discursive practices of politicians and journalists on social media. For this we need more annotated data than we currently have but the annotation process is time-consuming and costly. In this paper we examine machine learning methods for automatically annotating unseen tweetsbased on a small set of manually annotated tweets. Forimproving the performance of the learner, we focus onmethods related to training data expansion, like artificialtraining data, active learning and incorporating languagemodels developed from unannotated text.

Original languageEnglish
Title of host publicationProceedings - 13th IEEE International Conference on eScience, eScience 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages438-439
Number of pages2
ISBN (Electronic)9781538626863
Publication statusPublished - 14-Nov-2017
Event13th IEEE International Conference on eScience, eScience 2017 - Auckland, New Zealand
Duration: 24-Oct-201727-Oct-2017

Conference

Conference13th IEEE International Conference on eScience, eScience 2017
CountryNew Zealand
CityAuckland
Period24/10/201727/10/2017

Event

13th IEEE International Conference on eScience, eScience 2017

24/10/201727/10/2017

Auckland, New Zealand

Event: Conference

    Keywords

  • machine learning, political science, social media, Twitter

View graph of relations

ID: 109565001