Summary of The “colonial Impulse” Of Natural Language Processing: An Audit Of Bengali Sentiment Analysis Tools and Their Identity-based Biases, by Dipto Das and Shion Guha and Jed Brubaker and Bryan Semaan
The “Colonial Impulse” of Natural Language Processing: An Audit of Bengali Sentiment Analysis Tools and Their Identity-based Biases
by Dipto Das, Shion Guha, Jed Brubaker, Bryan Semaan
First submitted to arxiv on: 19 Jan 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Computers and Society (cs.CY); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This research paper investigates how sentiment analysis tools can perpetuate colonial values and biases, particularly in the context of Bengali communities that have been impacted by colonialism. The authors analyzed various sentiment analysis tools available for Bengali on Python package index (PyPI) and GitHub, focusing on gender, religion, and nationality. They found inconsistencies in output between different tools and bias towards certain identity categories, even when using similar semantic content and structure. The study highlights the importance of considering colonially shaped sociocultural structures to understand how sentiment analysis tools can perpetuate biases. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Sentiment analysis tools are used to guide many practices, including content moderation. However, these tools can also perpetuate colonial values and biases. This paper explores potential bias in sentiment analysis tools for Bengali communities that have experienced the impacts of colonialism. The authors analyzed various tools available on PyPI and GitHub and found that they exhibit bias towards certain identity categories and respond differently to different ways of identity expression. This study shows how sentiment analysis tools can perpetuate biases and highlights the importance of considering colonially shaped sociocultural structures. |
