We examine the extent to which we are able to automatically identify constructive online comments. We build several classifiers using New York Times Picks as positive examples and non-constructive thread comments from the Yahoo News Annotated Comments Corpus as negative examples of constructive online comments. We evaluate these classifiers on a crowdannotated corpus containing 1,121 comments. Our best classifier achieves a top F1 score of 0.84.
CITATION STYLE
Kolhatkar, V., & Taboada, M. (2017). Using new york times picks to identify constructive comments. In EMNLP 2017 - 2nd Workshop on Natural Language Processing Meets Journalism, NLPmJ 2017 - Proceedings of the Workshop (pp. 100–105). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/w17-4218
Mendeley helps you to discover research relevant for your work.