Why Do Document-Level Polarity Classifiers Fail?

Karen Martins, Pedro O.S Vaz-de-Melo, Rodrygo Santos


Abstract
Machine learning solutions are often criticized for the lack of explanation of their successes and failures. Understanding which instances are misclassified and why is essential to improve the learning process. This work helps to fill this gap by proposing a methodology to characterize, quantify and measure the impact of hard instances in the task of polarity classification of movie reviews. We characterize such instances into two categories: neutrality, where the text does not convey a clear polarity, and discrepancy, where the polarity of the text is the opposite of its true rating. We quantify the number of hard instances in polarity classification of movie reviews and provide empirical evidence about the need to pay attention to such problematic instances, as they are much harder to classify, for both machine and human classifiers. To the best of our knowledge, this is the first systematic analysis of the impact of hard instances in polarity detection from well-formed textual reviews.
Anthology ID:
2021.naacl-main.143
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1782–1794
Language:
URL:
https://aclanthology.org/2021.naacl-main.143
DOI:
10.18653/v1/2021.naacl-main.143
Bibkey:
Cite (ACL):
Karen Martins, Pedro O.S Vaz-de-Melo, and Rodrygo Santos. 2021. Why Do Document-Level Polarity Classifiers Fail?. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1782–1794, Online. Association for Computational Linguistics.
Cite (Informal):
Why Do Document-Level Polarity Classifiers Fail? (Martins et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.143.pdf
Video:
 https://aclanthology.org/2021.naacl-main.143.mp4
Code
 karenstemartins/NAACL2021