The Community for Technology Leaders
2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) (2018)
Barcelona, Spain
Aug. 28, 2018 to Aug. 31, 2018
ISSN: 2473-9928
ISBN: 978-1-5386-6052-2
pp: 552-559
Ying Lin , Rensselaer Polytechnic Institute, Computer Science Department, Troy, NY, USA
Joe Hoover , University of Southern California, Department of Psychology, Los Angeles, CA, USA
Gwenyth Portillo-Wightman , University of Southern California, Department of Psychology, Los Angeles, CA, USA
Christina Park , University of Southern California, Department of Psychology, Los Angeles, CA, USA
Morteza Dehghani , University of Southern California, Department of Psychology and Department of Computer Science, Los Angeles, CA, USA
Heng Ji , Rensselaer Polytechnic Institute, Computer Science Department, Troy, NY, USA
ABSTRACT
We address the problem of detecting expressions of moral values in tweets using content analysis. This is a particularly challenging problem because moral values are often only implicitly signaled in language, and tweets contain little contextual information due to length constraints. To address these obstacles, we present a novel approach to automatically acquire background knowledge from an external knowledge base to enrich input texts and thus improve moral value prediction. By combining basic textual features with background knowledge, our overall context-aware framework achieves performance comparable to a single human annotator. Our approach obtains 13.3% absolute F -score gains compared to our baseline model that only uses textual features. 11Our code is available at https://github.com/limteng-rpi/mvp
INDEX TERMS
Moral Value Prediction, Background Knowledge, Entity Linking, Natural Language Processing
CITATION

Y. Lin, J. Hoover, G. Portillo-Wightman, C. Park, M. Dehghani and H. Ji, "Acquiring Background Knowledge to Improve Moral Value Prediction," 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), Barcelona, Spain, 2018, pp. 552-559.
doi:10.1109/ASONAM.2018.8508244
178 ms
(Ver 3.3 (11022016))