Analyzing the sensitivity of Deep Neural Networks for sentiment analysis: a scoring approach

Ahoud Alhazmi, Wei Emma Zhang, Quan Z. Sheng, Abdulwahab Aljubairy

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

2 Citations (Scopus)


Deep Neural Networks (DNNs) have gained significant popularity in various Natural Language Processing tasks. However, the lack of interpretability of DNNs induces challenges to evaluate the robustness of DNNs. In this paper, we particularly focus on DNNs on sentiment analysis and conduct an empirical investigation on the sensitivity of DNNs. Specifically, we apply a scoring function to rank words importance without depending on the parameters or structure of the deep neural model. Then, we scan characteristics of these words to identify the model's weakness and perturb words to craft targeted attacks that exploit this weakness. We conduct extensive experiments on different neural network models across several real-world datasets. We report four intriguing findings: i) modern deep learning models for sentiment analysis ignore important sentiment terms such as opinion adjectives (i.e., amazing or terrible), ii) adjective words contribute to fooling sentiment analysis models more than other Parts-of-Speech (POS) categories, iii) changing or removing up to 10 adjectives words in a review text only decreases the accuracy up to 2%, and iv) modern models are unable to recognize the difference between an objective and a subjective review text.

Original languageEnglish
Title of host publication2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages7
ISBN (Electronic)9781728169262
Publication statusPublished - 2020
Event2020 International Joint Conference on Neural Networks - Virtual, Glasgow, United Kingdom
Duration: 19 Jul 202024 Jul 2020

Publication series

NameIEEE International Joint Conference on Neural Networks (IJCNN)
ISSN (Print)2161-4393


Conference2020 International Joint Conference on Neural Networks
Abbreviated titleIJCNN 2020
Country/TerritoryUnited Kingdom
CityVirtual, Glasgow


  • Adversarial Examples
  • Deep Neural Networks
  • Sentiment Analysis


Dive into the research topics of 'Analyzing the sensitivity of Deep Neural Networks for sentiment analysis: a scoring approach'. Together they form a unique fingerprint.

Cite this