Abstract
We study the problem of automatically identifying humorous text from a new kind of text data, i.e., online reviews. We propose a generative language model, based on the theory of incongruity, to model humorous text, which allows us to leverage background text sources, such as Wikipedia entry descriptions, and enables construction of multiple features for identifying humorous reviews. Evaluation of these features using supervised learning for classifying reviews into humorous and non-humorous reviews shows that the features constructed based on the proposed generative model are much more effective than the major features proposed in the existing literature, allowing us to achieve almost 86% accuracy. These humorous review predictions can also supply good indicators for identifying helpful reviews.- Anthology ID:
- D17-1051
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 492–501
- Language:
- URL:
- https://aclanthology.org/D17-1051
- DOI:
- 10.18653/v1/D17-1051
- Cite (ACL):
- Alex Morales and Chengxiang Zhai. 2017. Identifying Humor in Reviews using Background Text Sources. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 492–501, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Identifying Humor in Reviews using Background Text Sources (Morales & Zhai, EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/D17-1051.pdf